From b5f9744dd63b1d8eb8acc2fb863c7137a35b0b1e Mon Sep 17 00:00:00 2001 From: Pranay Gosar Date: Wed, 17 Apr 2024 12:33:10 -0500 Subject: [PATCH 1/8] add multi edit capability --- edit_utils.py | 169 +- inference_speech_editing.ipynb | 4550 ++++++++++++++++++++++++++++++-- 2 files changed, 4384 insertions(+), 335 deletions(-) diff --git a/edit_utils.py b/edit_utils.py index a9683f8..3a6883d 100644 --- a/edit_utils.py +++ b/edit_utils.py @@ -1,49 +1,120 @@ -def get_span(orig, new, editType): - orig_list = orig.split(" ") - new_list = new.split(" ") - - flag = False # this indicate whether the actual edit follow the specified editType - if editType == "deletion": - assert len(orig_list) > len(new_list), f"the edit type is deletion, but new is not shorter than original:\n new: {new}\n orig: {orig}" - diff = len(orig_list) - len(new_list) - for i, (o, n) in enumerate(zip(orig_list, new_list)): - if o != n: # assume the index of the first different word is the starting index of the orig_span - - orig_span = [i, i + diff - 1] # assume that the indices are starting and ending index of the deleted part - new_span = [i-1, i] # but for the new span, the starting and ending index is the two words that surround the deleted part - flag = True - break - - - elif editType == "insertion": - assert len(orig_list) < len(new_list), f"the edit type is insertion, but the new is not longer than the original:\n new: {new}\n orig: {orig}" - diff = len(new_list) - len(orig_list) - for i, (o, n) in enumerate(zip(orig_list, new_list)): - if o != n: # insertion is just the opposite of deletion - new_span = [i, i + diff - 1] # NOTE if only inserted one word, s and e will be the same - orig_span = [i-1, i] - flag = True - break - - elif editType == "substitution": - new_span = [] - orig_span = [] - for i, (o, n) in enumerate(zip(orig_list, new_list)): - if o != n: - new_span = [i] - orig_span = [i] - break - assert len(new_span) == 1 and len(orig_span) == 1, f"new_span: {new_span}, orig_span: {orig_span}" - for j, (o, n) in enumerate(zip(orig_list[::-1], new_list[::-1])): - if o != n: - new_span.append(len(new_list) - j -1) - orig_span.append(len(orig_list) - j - 1) - flag = True - break - else: - raise RuntimeError(f"editType unknown: {editType}") - - if not flag: - raise RuntimeError(f"wrong editing with the specified edit type:\n original: {orig}\n new: {new}\n, editType: {editType}") - - return orig_span, new_span \ No newline at end of file +import re + + +def levenshtein_distance(word1, word2): + len1, len2 = len(word1), len(word2) + # Initialize a matrix to store the edit distances, operations, and positions + dp = [[(0, "", []) for _ in range(len2 + 1)] for _ in range(len1 + 1)] + + # Initialize the first row and column + for i in range(len1 + 1): + dp[i][0] = (i, "d" * i) + for j in range(len2 + 1): + dp[0][j] = (j, "i" * j) + + # Fill in the rest of the matrix + for i in range(1, len1 + 1): + for j in range(1, len2 + 1): + cost = 0 if word1[i - 1] == word2[j - 1] else 1 + # Minimum of deletion, insertion, or substitution + deletion = dp[i - 1][j][0] + 1 + insertion = dp[i][j - 1][0] + 1 + substitution = dp[i - 1][j - 1][0] + cost + min_dist = min(deletion, insertion, substitution) + + # which operation led to the minimum distance + if min_dist == deletion: + operation = dp[i - 1][j][1] + "d" + elif min_dist == insertion: + operation = dp[i][j - 1][1] + "i" + else: + operation = dp[i - 1][j - 1][1] + ("s" if cost else "=") + + dp[i][j] = (min_dist, operation) + + # min edit distance, list of operations, positions of operations + return dp[len1][len2][0], dp[len1][len2][1] + + +def extract_words(sentence): + words = re.findall(r"\b\w+\b", sentence) + return words + +# edge cases for spans of deletion, insertion, substitution +def handle_delete(start, end, orig, new): + orig.append([start, end - 1]) + new.append([start - 1, start]) + +def handle_insert(start, end, orig, new): + temp_new = [start - 1, start] + orig.append(temp_new) + new.append(orig[-1]) + orig[-1], new[-1] = new[-1], temp_new + +def handle_substitute(start, end, orig, new): + orig.append([start, end - 1]) + new.append([start, end - 1]) + +# editing the last index of the sentence is another edge case +def handle_last_operation(prev_op, start, end, orig, new): + if prev_op == 'd': + handle_delete(start, end, orig, new) + elif prev_op == 'i': + handle_insert(start, end, orig, new) + elif prev_op == 's': + handle_substitute(start, end, orig, new) + +# adjust spans according to edge case expected output +def adjust_last_span(operations, orig, new): + if operations[-1] == 'd': + new[-1] = [new[-1][0] - 1, new[-1][1] - 1] + orig[-1] = [orig[-1][0] - 1, orig[-1][0] - 1] + elif operations[-1] == 'i': + new[-1] = [new[-1][0] - 1, new[-1][1] - 1] + orig[-1] = [orig[-1][0] - 1, orig[-1][0]] + +def get_spans(operations): + orig = [] + new = [] + prev_op = None + start = 0 + end = 0 + for i, op in enumerate(operations): + # prevent span duplication of sequential edits of the same type + if op != '=': + if op != prev_op: + if prev_op: + handle_last_operation(prev_op, start, end, orig, new) + prev_op = op + start = i + end = i + 1 + else: + if prev_op: + handle_last_operation(prev_op, start, end, orig, new) + prev_op = None + start = end + # edge case of last operation + if prev_op: + handle_last_operation(prev_op, start, end, orig, new) + adjust_last_span(operations, orig, new) + return orig, new + +def get_edits(operations): + used_edits = [] + prev_op = '' + for op in operations: + if op == 'i' and prev_op != 'i': + used_edits.append("insertion") + elif op == 'd' and prev_op != 'd': + used_edits.append("deletion") + elif op == 's' and prev_op != 's': + used_edits.append("substitution") + prev_op = op + return used_edits + +def parse_edit(orig_transcript, trgt_transcript): + word1 = extract_words(orig_transcript) + word2 = extract_words(trgt_transcript) + distance, operations = levenshtein_distance(word1, word2) + orig_span, new_span = get_spans(operations) + return operations, orig_span, new_span \ No newline at end of file diff --git a/inference_speech_editing.ipynb b/inference_speech_editing.ipynb index 022e3ba..2edef05 100644 --- a/inference_speech_editing.ipynb +++ b/inference_speech_editing.ipynb @@ -1,301 +1,4279 @@ { - "cells": [ - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [], - "source": [ - "import os\n", - "os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\" \n", - "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"7\"\n", - "os.environ[\"USER\"] = \"YOUR_USERNAME\" # TODO change this to your username" - ] + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "gpuType": "T4" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU" }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ + "cells": [ { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/pyp/miniconda3/envs/voicecraft/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", - " from .autonotebook import tqdm as notebook_tqdm\n" - ] - } - ], - "source": [ - "# import libs\n", - "import torch\n", - "import torchaudio\n", - "import numpy as np\n", - "import random\n", - "\n", - "from data.tokenizer import (\n", - " AudioTokenizer,\n", - " TextTokenizer,\n", - ")\n", - "\n", - "from models import voicecraft" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# install MFA models and dictionaries if you haven't done so already\n", - "!source ~/.bashrc && \\\n", - " conda activate voicecraft && \\\n", - " mfa model download dictionary english_us_arpa && \\\n", - " mfa model download acoustic english_us_arpa" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [], - "source": [ - "# hyperparameters for inference\n", - "left_margin = 0.08\n", - "right_margin = 0.08\n", - "codec_audio_sr = 16000\n", - "codec_sr = 50\n", - "top_k = 0\n", - "top_p = 0.8\n", - "temperature = 1\n", - "kvcache = 0\n", - "# adjust the below three arguments if the generation is not as good\n", - "seed = 1 # random seed magic\n", - "silence_tokens = [1388,1898,131] # if there are long silence in the generated audio, reduce the stop_repetition to 3, 2 or even 1\n", - "stop_repetition = -1 # -1 means do not adjust prob of silence tokens. if there are long silence or unnaturally strecthed words, increase sample_batch_size to 2, 3 or even 4\n", - "# what this will do to the model is that the model will run sample_batch_size examples of the same audio, and pick the one that's the shortest\n", - "def seed_everything(seed):\n", - " os.environ['PYTHONHASHSEED'] = str(seed)\n", - " random.seed(seed)\n", - " np.random.seed(seed)\n", - " torch.manual_seed(seed)\n", - " torch.cuda.manual_seed(seed)\n", - " torch.backends.cudnn.benchmark = False\n", - " torch.backends.cudnn.deterministic = True\n", - "seed_everything(seed)\n", - "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", - "\n", - "# point to the original file or record the file\n", - "# write down the transcript for the file, or run whisper to get the transcript (and you can modify it if it's not accurate), save it as a .txt file\n", - "orig_audio = \"./demo/84_121550_000074_000000.wav\"\n", - "orig_transcript = \"But when I had approached so near to them The common object, which the sense deceives, Lost not by distance any of its marks,\"\n", - "# move the audio and transcript to temp folder\n", - "temp_folder = \"./demo/temp\"\n", - "os.makedirs(temp_folder, exist_ok=True)\n", - "os.system(f\"cp {orig_audio} {temp_folder}\")\n", - "filename = os.path.splitext(orig_audio.split(\"/\")[-1])[0]\n", - "with open(f\"{temp_folder}/{filename}.txt\", \"w\") as f:\n", - " f.write(orig_transcript)\n", - "# run MFA to get the alignment\n", - "align_temp = f\"{temp_folder}/mfa_alignments\"\n", - "os.makedirs(align_temp, exist_ok=True)\n", - "os.system(f\"mfa align -j 1 --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp}\")\n", - "# if it fail, it could be because the audio is too hard for the alignment model, increasing the beam size usually solves the issue\n", - "# os.system(f\"mfa align -j 1 --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp} --beam 1000 --retry_beam 2000\")\n", - "audio_fn = f\"{temp_folder}/{filename}.wav\"\n", - "transcript_fn = f\"{temp_folder}/{filename}.txt\"\n", - "align_fn = f\"{align_temp}/{filename}.csv\"\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [ + "cell_type": "markdown", + "source": [ + "### This will crash the kernel the first time. This is expected - if you rerun from the start, it will work." + ], + "metadata": { + "id": "2qVBkPyM4-Fc" + } + }, + { + "cell_type": "code", + "source": [ + "!apt-get install -y git-core ffmpeg espeak-ng\n", + "!pip install -q condacolab\n", + "import condacolab\n", + "condacolab.install()\n", + "condacolab.check()" + ], + "metadata": { + "id": "OHGB5aX75EZ7", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "d102e3c9-e2c5-40e0-bde0-3c1a78ca82cc" + }, + "execution_count": 1, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Reading package lists... Done\n", + "Building dependency tree... Done\n", + "Reading state information... Done\n", + "Note, selecting 'git' instead of 'git-core'\n", + "espeak-ng is already the newest version (1.50+dfsg-10).\n", + "git is already the newest version (1:2.34.1-1ubuntu1.10).\n", + "ffmpeg is already the newest version (7:4.4.2-0ubuntu0.22.04.1).\n", + "0 upgraded, 0 newly installed, 0 to remove and 45 not upgraded.\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0m✨🍰✨ Everything looks OK!\n", + "✨🍰✨ Everything looks OK!\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!echo -e \"Grab a cup a coffee and a slice of pizza...\\n\\n\"\n", + "!conda install -y -c conda-forge montreal-forced-aligner=2.2.17 openfst=1.8.2 kaldi=5.5.1068 && \\\n", + " pip install torch==2.1.0 && \\\n", + " pip install tensorboard==2.16.2 && \\\n", + " pip install phonemizer==3.2.1 && \\\n", + " pip install torchaudio==2.1.0 && \\\n", + " pip install datasets==2.16.0 && \\\n", + " pip install torchmetrics==0.11.1 && \\\n", + " pip install torchvision==0.16.0\n", + "\n", + "!pip install -U git+https://git@github.com/facebookresearch/audiocraft#egg=audiocraft\n", + "!git clone https://github.com/jasonppy/VoiceCraft.git" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Z57Oocvy5ILk", + "outputId": "1e75f151-05da-4763-a07b-45ff445edb94" + }, + "execution_count": 2, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Grab a cup a coffee and a slice of pizza...\n", + "\n", + "\n", + "Channels:\n", + " - conda-forge\n", + "Platform: linux-64\n", + "Collecting package metadata (repodata.json): - \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\bdone\n", + "Solving environment: \\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\bdone\n", + "\n", + "\n", + "==> WARNING: A newer version of conda exists. <==\n", + " current version: 23.11.0\n", + " latest version: 24.3.0\n", + "\n", + "Please update conda by running\n", + "\n", + " $ conda update -n base -c conda-forge conda\n", + "\n", + "\n", + "\n", + "## Package Plan ##\n", + "\n", + " environment location: /usr/local\n", + "\n", + " added / updated specs:\n", + " - kaldi=5.5.1068\n", + " - montreal-forced-aligner=2.2.17\n", + " - openfst=1.8.2\n", + "\n", + "\n", + "The following packages will be downloaded:\n", + "\n", + " package | build\n", + " ---------------------------|-----------------\n", + " aom-3.7.1 | h59595ed_0 2.6 MB conda-forge\n", + " atk-1.0-2.38.0 | hd4edc92_1 539 KB conda-forge\n", + " audioread-3.0.1 | py310hff52083_1 36 KB conda-forge\n", + " baumwelch-0.3.7 | h00ab1b0_5 376 KB conda-forge\n", + " biopython-1.79 | py310h5764c6d_3 2.7 MB conda-forge\n", + " brotli-1.1.0 | hd590300_1 19 KB conda-forge\n", + " brotli-bin-1.1.0 | hd590300_1 19 KB conda-forge\n", + " ca-certificates-2024.2.2 | hbcca054_0 152 KB conda-forge\n", + " cairo-1.18.0 | h3faef2a_0 959 KB conda-forge\n", + " certifi-2024.2.2 | pyhd8ed1ab_0 157 KB conda-forge\n", + " click-8.1.7 |unix_pyh707e725_0 82 KB conda-forge\n", + " contourpy-1.2.1 | py310hd41b1e2_0 236 KB conda-forge\n", + " cudatoolkit-11.8.0 | h4ba93d1_13 682.5 MB conda-forge\n", + " cycler-0.12.1 | pyhd8ed1ab_0 13 KB conda-forge\n", + " cython-3.0.10 | py310hc6cd4ac_0 3.1 MB conda-forge\n", + " dataclassy-1.0.1 | pyhd8ed1ab_0 31 KB conda-forge\n", + " dav1d-1.2.1 | hd590300_0 742 KB conda-forge\n", + " decorator-5.1.1 | pyhd8ed1ab_0 12 KB conda-forge\n", + " expat-2.6.2 | h59595ed_0 134 KB conda-forge\n", + " ffmpeg-6.1.1 | gpl_h186bccc_100 9.3 MB conda-forge\n", + " font-ttf-dejavu-sans-mono-2.37| hab24e00_0 388 KB conda-forge\n", + " font-ttf-inconsolata-3.000 | h77eed37_0 94 KB conda-forge\n", + " font-ttf-source-code-pro-2.038| h77eed37_0 684 KB conda-forge\n", + " font-ttf-ubuntu-0.83 | h77eed37_1 1.5 MB conda-forge\n", + " fontconfig-2.14.2 | h14ed4e7_0 266 KB conda-forge\n", + " fonts-conda-ecosystem-1 | 0 4 KB conda-forge\n", + " fonts-conda-forge-1 | 0 4 KB conda-forge\n", + " fonttools-4.51.0 | py310h2372a71_0 2.2 MB conda-forge\n", + " freetype-2.12.1 | h267a509_2 620 KB conda-forge\n", + " fribidi-1.0.10 | h36c2ea0_0 112 KB conda-forge\n", + " gdk-pixbuf-2.42.10 | h829c605_6 563 KB conda-forge\n", + " gettext-0.22.5 | h59595ed_2 464 KB conda-forge\n", + " gettext-tools-0.22.5 | h59595ed_2 2.6 MB conda-forge\n", + " giflib-5.2.2 | hd590300_0 75 KB conda-forge\n", + " gmp-6.3.0 | h59595ed_1 556 KB conda-forge\n", + " gnutls-3.7.9 | hb077bed_0 1.9 MB conda-forge\n", + " graphite2-1.3.13 | h59595ed_1003 95 KB conda-forge\n", + " graphviz-9.0.0 | h78e8752_1 2.2 MB conda-forge\n", + " greenlet-3.0.3 | py310hc6cd4ac_0 206 KB conda-forge\n", + " gtk2-2.24.33 | h280cfa0_4 6.2 MB conda-forge\n", + " gts-0.7.6 | h977cf35_4 311 KB conda-forge\n", + " harfbuzz-8.3.0 | h3d44ed6_0 1.5 MB conda-forge\n", + " hdbscan-0.8.33 | py310h1f7b6fc_4 505 KB conda-forge\n", + " importlib-metadata-7.1.0 | pyha770c72_0 26 KB conda-forge\n", + " joblib-1.4.0 | pyhd8ed1ab_0 215 KB conda-forge\n", + " kaldi-5.5.1068 |cuda112h971fcfb_2 22.6 MB conda-forge\n", + " kiwisolver-1.4.5 | py310hd41b1e2_1 71 KB conda-forge\n", + " kneed-0.8.5 | pyhd8ed1ab_0 15 KB conda-forge\n", + " lame-3.100 | h166bdaf_1003 496 KB conda-forge\n", + " lazy_loader-0.4 | pyhd8ed1ab_0 16 KB conda-forge\n", + " lcms2-2.16 | hb7c19ff_0 239 KB conda-forge\n", + " lerc-4.0.0 | h27087fc_0 275 KB conda-forge\n", + " libasprintf-0.22.5 | h661eb56_2 42 KB conda-forge\n", + " libasprintf-devel-0.22.5 | h661eb56_2 33 KB conda-forge\n", + " libass-0.17.1 | h8fe9dca_1 124 KB conda-forge\n", + " libblas-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", + " libbrotlicommon-1.1.0 | hd590300_1 68 KB conda-forge\n", + " libbrotlidec-1.1.0 | hd590300_1 32 KB conda-forge\n", + " libbrotlienc-1.1.0 | hd590300_1 276 KB conda-forge\n", + " libcblas-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", + " libdeflate-1.20 | hd590300_0 70 KB conda-forge\n", + " libdrm-2.4.120 | hd590300_0 296 KB conda-forge\n", + " libexpat-2.6.2 | h59595ed_0 72 KB conda-forge\n", + " libflac-1.4.3 | h59595ed_0 385 KB conda-forge\n", + " libgd-2.3.3 | h119a65a_9 219 KB conda-forge\n", + " libgettextpo-0.22.5 | h59595ed_2 167 KB conda-forge\n", + " libgettextpo-devel-0.22.5 | h59595ed_2 36 KB conda-forge\n", + " libgfortran-ng-13.2.0 | h69a702a_5 23 KB conda-forge\n", + " libgfortran5-13.2.0 | ha4646dd_5 1.4 MB conda-forge\n", + " libglib-2.80.0 | hf2295e7_5 3.7 MB conda-forge\n", + " libidn2-2.3.7 | hd590300_0 124 KB conda-forge\n", + " libjpeg-turbo-3.0.0 | hd590300_1 604 KB conda-forge\n", + " liblapack-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", + " liblapacke-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", + " libllvm14-14.0.6 | hcd5def8_4 30.0 MB conda-forge\n", + " libmagma-2.7.1 | hc72dce7_6 201.2 MB conda-forge\n", + " libmagma_sparse-2.7.1 | h8354cda_6 7.1 MB conda-forge\n", + " libogg-1.3.4 | h7f98852_1 206 KB conda-forge\n", + " libopenblas-0.3.27 |pthreads_h413a1c8_0 5.3 MB conda-forge\n", + " libopus-1.3.1 | h7f98852_1 255 KB conda-forge\n", + " libpciaccess-0.18 | hd590300_0 28 KB conda-forge\n", + " libpng-1.6.43 | h2797004_0 281 KB conda-forge\n", + " libpq-16.1 | h33b98f1_7 2.4 MB conda-forge\n", + " librosa-0.10.1 | pyhd8ed1ab_0 189 KB conda-forge\n", + " librsvg-2.56.3 | he3f83f7_1 5.6 MB conda-forge\n", + " libsndfile-1.2.2 | hc60ed4a_1 346 KB conda-forge\n", + " libtasn1-4.19.0 | h166bdaf_0 114 KB conda-forge\n", + " libtiff-4.6.0 | h1dd3fc0_3 276 KB conda-forge\n", + " libunistring-0.9.10 | h7f98852_0 1.4 MB conda-forge\n", + " libva-2.21.0 | hd590300_0 185 KB conda-forge\n", + " libvorbis-1.3.7 | h9c3ff4c_0 280 KB conda-forge\n", + " libvpx-1.13.1 | h59595ed_0 982 KB conda-forge\n", + " libwebp-1.3.2 | h658648e_1 83 KB conda-forge\n", + " libwebp-base-1.3.2 | hd590300_1 424 KB conda-forge\n", + " libxcb-1.15 | h0b41bf4_0 375 KB conda-forge\n", + " llvmlite-0.42.0 | py310h1b8f574_1 3.2 MB conda-forge\n", + " mad-0.15.1b | h9c3ff4c_1 113 KB conda-forge\n", + " magma-2.7.1 | ha770c72_6 100 KB conda-forge\n", + " markdown-it-py-3.0.0 | pyhd8ed1ab_0 63 KB conda-forge\n", + " matplotlib-base-3.8.4 | py310h62c0568_0 6.7 MB conda-forge\n", + " mdurl-0.1.2 | pyhd8ed1ab_0 14 KB conda-forge\n", + " montreal-forced-aligner-2.2.17| pyhd8ed1ab_0 225 KB conda-forge\n", + " mpg123-1.32.6 | h59595ed_0 480 KB conda-forge\n", + " msgpack-python-1.0.7 | py310hd41b1e2_0 192 KB conda-forge\n", + " munkres-1.1.4 | pyh9f0ad1d_0 12 KB conda-forge\n", + " nettle-3.9.1 | h7ab15ed_0 988 KB conda-forge\n", + " ngram-1.3.14 | h924138e_2 3.4 MB conda-forge\n", + " numba-0.59.1 | py310h7dc5dd1_0 4.1 MB conda-forge\n", + " numpy-1.26.4 | py310hb13e2d6_0 6.7 MB conda-forge\n", + " openfst-1.8.2 | h924138e_2 7.4 MB conda-forge\n", + " openh264-2.4.0 | h59595ed_0 719 KB conda-forge\n", + " openjpeg-2.5.2 | h488ebb8_0 334 KB conda-forge\n", + " openssl-3.2.1 | hd590300_1 2.7 MB conda-forge\n", + " p11-kit-0.24.1 | hc5aa10d_0 4.5 MB conda-forge\n", + " pandas-2.2.2 | py310hcc13569_0 12.4 MB conda-forge\n", + " pango-1.52.2 | ha41ecd1_0 436 KB conda-forge\n", + " patsy-0.5.6 | pyhd8ed1ab_0 183 KB conda-forge\n", + " pcre2-10.43 | hcad00b1_0 929 KB conda-forge\n", + " pgvector-0.6.0 | h634da08_0 66 KB conda-forge\n", + " pgvector-python-0.2.5 | pyhe093146_0 14 KB conda-forge\n", + " pillow-10.3.0 | py310hf73ecf8_0 39.8 MB conda-forge\n", + " pixman-0.43.2 | h59595ed_0 378 KB conda-forge\n", + " pooch-1.8.1 | pyhd8ed1ab_0 51 KB conda-forge\n", + " postgresql-16.1 | h7387d8b_7 5.1 MB conda-forge\n", + " praatio-6.0.0 | pyhd8ed1ab_0 60 KB conda-forge\n", + " psycopg2-2.9.9 | py310h275853b_0 169 KB conda-forge\n", + " pthread-stubs-0.4 | h36c2ea0_1001 5 KB conda-forge\n", + " pygments-2.17.2 | pyhd8ed1ab_0 840 KB conda-forge\n", + " pynini-2.1.5 | py310hd41b1e2_6 1.5 MB conda-forge\n", + " pyparsing-3.1.2 | pyhd8ed1ab_0 87 KB conda-forge\n", + " pysoundfile-0.12.1 | pyhd8ed1ab_0 27 KB conda-forge\n", + " python-dateutil-2.9.0 | pyhd8ed1ab_0 218 KB conda-forge\n", + " python-tzdata-2024.1 | pyhd8ed1ab_0 141 KB conda-forge\n", + " pytz-2024.1 | pyhd8ed1ab_0 184 KB conda-forge\n", + " pyyaml-6.0.1 | py310h2372a71_1 167 KB conda-forge\n", + " rich-13.7.1 | pyhd8ed1ab_0 180 KB conda-forge\n", + " rich-click-1.7.4 | pyhd8ed1ab_0 32 KB conda-forge\n", + " scikit-learn-1.2.2 | py310hf7d194e_2 7.3 MB conda-forge\n", + " scipy-1.13.0 | py310hb13e2d6_0 15.6 MB conda-forge\n", + " seaborn-0.13.2 | hd8ed1ab_0 7 KB conda-forge\n", + " seaborn-base-0.13.2 | pyhd8ed1ab_0 229 KB conda-forge\n", + " six-1.16.0 | pyh6c4a22f_0 14 KB conda-forge\n", + " sox-14.4.2 | ha5cc309_1018 499 KB conda-forge\n", + " soxr-0.1.3 | h0b41bf4_3 128 KB conda-forge\n", + " soxr-python-0.3.7 | py310h1f7b6fc_0 265 KB conda-forge\n", + " sqlalchemy-2.0.29 | py310h2372a71_0 2.7 MB conda-forge\n", + " sqlite-3.44.2 | h2c6b66d_0 817 KB conda-forge\n", + " statsmodels-0.14.1 | py310h1f7b6fc_0 10.5 MB conda-forge\n", + " svt-av1-1.8.0 | h59595ed_0 2.5 MB conda-forge\n", + " threadpoolctl-3.4.0 | pyhc1e730c_0 22 KB conda-forge\n", + " typing-extensions-4.11.0 | hd8ed1ab_0 10 KB conda-forge\n", + " typing_extensions-4.11.0 | pyha770c72_0 37 KB conda-forge\n", + " tzcode-2024a | h3f72095_0 68 KB conda-forge\n", + " unicodedata2-15.1.0 | py310h2372a71_0 365 KB conda-forge\n", + " x264-1!164.3095 | h166bdaf_2 877 KB conda-forge\n", + " x265-3.5 | h924138e_3 3.2 MB conda-forge\n", + " xorg-fixesproto-5.0 | h7f98852_1002 9 KB conda-forge\n", + " xorg-kbproto-1.0.7 | h7f98852_1002 27 KB conda-forge\n", + " xorg-libice-1.1.1 | hd590300_0 57 KB conda-forge\n", + " xorg-libsm-1.2.4 | h7391055_0 27 KB conda-forge\n", + " xorg-libx11-1.8.9 | h8ee46fc_0 809 KB conda-forge\n", + " xorg-libxau-1.0.11 | hd590300_0 14 KB conda-forge\n", + " xorg-libxdmcp-1.1.3 | h7f98852_0 19 KB conda-forge\n", + " xorg-libxext-1.3.4 | h0b41bf4_2 49 KB conda-forge\n", + " xorg-libxfixes-5.0.3 | h7f98852_1004 18 KB conda-forge\n", + " xorg-libxrender-0.9.11 | hd590300_0 37 KB conda-forge\n", + " xorg-renderproto-0.11.1 | h7f98852_1002 9 KB conda-forge\n", + " xorg-xextproto-7.3.0 | h0b41bf4_1003 30 KB conda-forge\n", + " xorg-xproto-7.0.31 | h7f98852_1007 73 KB conda-forge\n", + " yaml-0.2.5 | h7f98852_2 87 KB conda-forge\n", + " zipp-3.17.0 | pyhd8ed1ab_0 19 KB conda-forge\n", + " zlib-1.2.13 | hd590300_5 91 KB conda-forge\n", + " ------------------------------------------------------------\n", + " Total: 1.14 GB\n", + "\n", + "The following NEW packages will be INSTALLED:\n", + "\n", + " aom conda-forge/linux-64::aom-3.7.1-h59595ed_0 \n", + " atk-1.0 conda-forge/linux-64::atk-1.0-2.38.0-hd4edc92_1 \n", + " audioread conda-forge/linux-64::audioread-3.0.1-py310hff52083_1 \n", + " baumwelch conda-forge/linux-64::baumwelch-0.3.7-h00ab1b0_5 \n", + " biopython conda-forge/linux-64::biopython-1.79-py310h5764c6d_3 \n", + " brotli conda-forge/linux-64::brotli-1.1.0-hd590300_1 \n", + " brotli-bin conda-forge/linux-64::brotli-bin-1.1.0-hd590300_1 \n", + " cairo conda-forge/linux-64::cairo-1.18.0-h3faef2a_0 \n", + " click conda-forge/noarch::click-8.1.7-unix_pyh707e725_0 \n", + " contourpy conda-forge/linux-64::contourpy-1.2.1-py310hd41b1e2_0 \n", + " cudatoolkit conda-forge/linux-64::cudatoolkit-11.8.0-h4ba93d1_13 \n", + " cycler conda-forge/noarch::cycler-0.12.1-pyhd8ed1ab_0 \n", + " cython conda-forge/linux-64::cython-3.0.10-py310hc6cd4ac_0 \n", + " dataclassy conda-forge/noarch::dataclassy-1.0.1-pyhd8ed1ab_0 \n", + " dav1d conda-forge/linux-64::dav1d-1.2.1-hd590300_0 \n", + " decorator conda-forge/noarch::decorator-5.1.1-pyhd8ed1ab_0 \n", + " expat conda-forge/linux-64::expat-2.6.2-h59595ed_0 \n", + " ffmpeg conda-forge/linux-64::ffmpeg-6.1.1-gpl_h186bccc_100 \n", + " font-ttf-dejavu-s~ conda-forge/noarch::font-ttf-dejavu-sans-mono-2.37-hab24e00_0 \n", + " font-ttf-inconsol~ conda-forge/noarch::font-ttf-inconsolata-3.000-h77eed37_0 \n", + " font-ttf-source-c~ conda-forge/noarch::font-ttf-source-code-pro-2.038-h77eed37_0 \n", + " font-ttf-ubuntu conda-forge/noarch::font-ttf-ubuntu-0.83-h77eed37_1 \n", + " fontconfig conda-forge/linux-64::fontconfig-2.14.2-h14ed4e7_0 \n", + " fonts-conda-ecosy~ conda-forge/noarch::fonts-conda-ecosystem-1-0 \n", + " fonts-conda-forge conda-forge/noarch::fonts-conda-forge-1-0 \n", + " fonttools conda-forge/linux-64::fonttools-4.51.0-py310h2372a71_0 \n", + " freetype conda-forge/linux-64::freetype-2.12.1-h267a509_2 \n", + " fribidi conda-forge/linux-64::fribidi-1.0.10-h36c2ea0_0 \n", + " gdk-pixbuf conda-forge/linux-64::gdk-pixbuf-2.42.10-h829c605_6 \n", + " gettext conda-forge/linux-64::gettext-0.22.5-h59595ed_2 \n", + " gettext-tools conda-forge/linux-64::gettext-tools-0.22.5-h59595ed_2 \n", + " giflib conda-forge/linux-64::giflib-5.2.2-hd590300_0 \n", + " gmp conda-forge/linux-64::gmp-6.3.0-h59595ed_1 \n", + " gnutls conda-forge/linux-64::gnutls-3.7.9-hb077bed_0 \n", + " graphite2 conda-forge/linux-64::graphite2-1.3.13-h59595ed_1003 \n", + " graphviz conda-forge/linux-64::graphviz-9.0.0-h78e8752_1 \n", + " greenlet conda-forge/linux-64::greenlet-3.0.3-py310hc6cd4ac_0 \n", + " gtk2 conda-forge/linux-64::gtk2-2.24.33-h280cfa0_4 \n", + " gts conda-forge/linux-64::gts-0.7.6-h977cf35_4 \n", + " harfbuzz conda-forge/linux-64::harfbuzz-8.3.0-h3d44ed6_0 \n", + " hdbscan conda-forge/linux-64::hdbscan-0.8.33-py310h1f7b6fc_4 \n", + " importlib-metadata conda-forge/noarch::importlib-metadata-7.1.0-pyha770c72_0 \n", + " joblib conda-forge/noarch::joblib-1.4.0-pyhd8ed1ab_0 \n", + " kaldi conda-forge/linux-64::kaldi-5.5.1068-cuda112h971fcfb_2 \n", + " kiwisolver conda-forge/linux-64::kiwisolver-1.4.5-py310hd41b1e2_1 \n", + " kneed conda-forge/noarch::kneed-0.8.5-pyhd8ed1ab_0 \n", + " lame conda-forge/linux-64::lame-3.100-h166bdaf_1003 \n", + " lazy_loader conda-forge/noarch::lazy_loader-0.4-pyhd8ed1ab_0 \n", + " lcms2 conda-forge/linux-64::lcms2-2.16-hb7c19ff_0 \n", + " lerc conda-forge/linux-64::lerc-4.0.0-h27087fc_0 \n", + " libasprintf conda-forge/linux-64::libasprintf-0.22.5-h661eb56_2 \n", + " libasprintf-devel conda-forge/linux-64::libasprintf-devel-0.22.5-h661eb56_2 \n", + " libass conda-forge/linux-64::libass-0.17.1-h8fe9dca_1 \n", + " libblas conda-forge/linux-64::libblas-3.9.0-22_linux64_openblas \n", + " libbrotlicommon conda-forge/linux-64::libbrotlicommon-1.1.0-hd590300_1 \n", + " libbrotlidec conda-forge/linux-64::libbrotlidec-1.1.0-hd590300_1 \n", + " libbrotlienc conda-forge/linux-64::libbrotlienc-1.1.0-hd590300_1 \n", + " libcblas conda-forge/linux-64::libcblas-3.9.0-22_linux64_openblas \n", + " libdeflate conda-forge/linux-64::libdeflate-1.20-hd590300_0 \n", + " libdrm conda-forge/linux-64::libdrm-2.4.120-hd590300_0 \n", + " libexpat conda-forge/linux-64::libexpat-2.6.2-h59595ed_0 \n", + " libflac conda-forge/linux-64::libflac-1.4.3-h59595ed_0 \n", + " libgd conda-forge/linux-64::libgd-2.3.3-h119a65a_9 \n", + " libgettextpo conda-forge/linux-64::libgettextpo-0.22.5-h59595ed_2 \n", + " libgettextpo-devel conda-forge/linux-64::libgettextpo-devel-0.22.5-h59595ed_2 \n", + " libgfortran-ng conda-forge/linux-64::libgfortran-ng-13.2.0-h69a702a_5 \n", + " libgfortran5 conda-forge/linux-64::libgfortran5-13.2.0-ha4646dd_5 \n", + " libglib conda-forge/linux-64::libglib-2.80.0-hf2295e7_5 \n", + " libidn2 conda-forge/linux-64::libidn2-2.3.7-hd590300_0 \n", + " libjpeg-turbo conda-forge/linux-64::libjpeg-turbo-3.0.0-hd590300_1 \n", + " liblapack conda-forge/linux-64::liblapack-3.9.0-22_linux64_openblas \n", + " liblapacke conda-forge/linux-64::liblapacke-3.9.0-22_linux64_openblas \n", + " libllvm14 conda-forge/linux-64::libllvm14-14.0.6-hcd5def8_4 \n", + " libmagma conda-forge/linux-64::libmagma-2.7.1-hc72dce7_6 \n", + " libmagma_sparse conda-forge/linux-64::libmagma_sparse-2.7.1-h8354cda_6 \n", + " libogg conda-forge/linux-64::libogg-1.3.4-h7f98852_1 \n", + " libopenblas conda-forge/linux-64::libopenblas-0.3.27-pthreads_h413a1c8_0 \n", + " libopus conda-forge/linux-64::libopus-1.3.1-h7f98852_1 \n", + " libpciaccess conda-forge/linux-64::libpciaccess-0.18-hd590300_0 \n", + " libpng conda-forge/linux-64::libpng-1.6.43-h2797004_0 \n", + " libpq conda-forge/linux-64::libpq-16.1-h33b98f1_7 \n", + " librosa conda-forge/noarch::librosa-0.10.1-pyhd8ed1ab_0 \n", + " librsvg conda-forge/linux-64::librsvg-2.56.3-he3f83f7_1 \n", + " libsndfile conda-forge/linux-64::libsndfile-1.2.2-hc60ed4a_1 \n", + " libtasn1 conda-forge/linux-64::libtasn1-4.19.0-h166bdaf_0 \n", + " libtiff conda-forge/linux-64::libtiff-4.6.0-h1dd3fc0_3 \n", + " libunistring conda-forge/linux-64::libunistring-0.9.10-h7f98852_0 \n", + " libva conda-forge/linux-64::libva-2.21.0-hd590300_0 \n", + " libvorbis conda-forge/linux-64::libvorbis-1.3.7-h9c3ff4c_0 \n", + " libvpx conda-forge/linux-64::libvpx-1.13.1-h59595ed_0 \n", + " libwebp conda-forge/linux-64::libwebp-1.3.2-h658648e_1 \n", + " libwebp-base conda-forge/linux-64::libwebp-base-1.3.2-hd590300_1 \n", + " libxcb conda-forge/linux-64::libxcb-1.15-h0b41bf4_0 \n", + " llvmlite conda-forge/linux-64::llvmlite-0.42.0-py310h1b8f574_1 \n", + " mad conda-forge/linux-64::mad-0.15.1b-h9c3ff4c_1 \n", + " magma conda-forge/linux-64::magma-2.7.1-ha770c72_6 \n", + " markdown-it-py conda-forge/noarch::markdown-it-py-3.0.0-pyhd8ed1ab_0 \n", + " matplotlib-base conda-forge/linux-64::matplotlib-base-3.8.4-py310h62c0568_0 \n", + " mdurl conda-forge/noarch::mdurl-0.1.2-pyhd8ed1ab_0 \n", + " montreal-forced-a~ conda-forge/noarch::montreal-forced-aligner-2.2.17-pyhd8ed1ab_0 \n", + " mpg123 conda-forge/linux-64::mpg123-1.32.6-h59595ed_0 \n", + " msgpack-python conda-forge/linux-64::msgpack-python-1.0.7-py310hd41b1e2_0 \n", + " munkres conda-forge/noarch::munkres-1.1.4-pyh9f0ad1d_0 \n", + " nettle conda-forge/linux-64::nettle-3.9.1-h7ab15ed_0 \n", + " ngram conda-forge/linux-64::ngram-1.3.14-h924138e_2 \n", + " numba conda-forge/linux-64::numba-0.59.1-py310h7dc5dd1_0 \n", + " numpy conda-forge/linux-64::numpy-1.26.4-py310hb13e2d6_0 \n", + " openfst conda-forge/linux-64::openfst-1.8.2-h924138e_2 \n", + " openh264 conda-forge/linux-64::openh264-2.4.0-h59595ed_0 \n", + " openjpeg conda-forge/linux-64::openjpeg-2.5.2-h488ebb8_0 \n", + " p11-kit conda-forge/linux-64::p11-kit-0.24.1-hc5aa10d_0 \n", + " pandas conda-forge/linux-64::pandas-2.2.2-py310hcc13569_0 \n", + " pango conda-forge/linux-64::pango-1.52.2-ha41ecd1_0 \n", + " patsy conda-forge/noarch::patsy-0.5.6-pyhd8ed1ab_0 \n", + " pcre2 conda-forge/linux-64::pcre2-10.43-hcad00b1_0 \n", + " pgvector conda-forge/linux-64::pgvector-0.6.0-h634da08_0 \n", + " pgvector-python conda-forge/noarch::pgvector-python-0.2.5-pyhe093146_0 \n", + " pillow conda-forge/linux-64::pillow-10.3.0-py310hf73ecf8_0 \n", + " pixman conda-forge/linux-64::pixman-0.43.2-h59595ed_0 \n", + " pooch conda-forge/noarch::pooch-1.8.1-pyhd8ed1ab_0 \n", + " postgresql conda-forge/linux-64::postgresql-16.1-h7387d8b_7 \n", + " praatio conda-forge/noarch::praatio-6.0.0-pyhd8ed1ab_0 \n", + " psycopg2 conda-forge/linux-64::psycopg2-2.9.9-py310h275853b_0 \n", + " pthread-stubs conda-forge/linux-64::pthread-stubs-0.4-h36c2ea0_1001 \n", + " pygments conda-forge/noarch::pygments-2.17.2-pyhd8ed1ab_0 \n", + " pynini conda-forge/linux-64::pynini-2.1.5-py310hd41b1e2_6 \n", + " pyparsing conda-forge/noarch::pyparsing-3.1.2-pyhd8ed1ab_0 \n", + " pysoundfile conda-forge/noarch::pysoundfile-0.12.1-pyhd8ed1ab_0 \n", + " python-dateutil conda-forge/noarch::python-dateutil-2.9.0-pyhd8ed1ab_0 \n", + " python-tzdata conda-forge/noarch::python-tzdata-2024.1-pyhd8ed1ab_0 \n", + " pytz conda-forge/noarch::pytz-2024.1-pyhd8ed1ab_0 \n", + " pyyaml conda-forge/linux-64::pyyaml-6.0.1-py310h2372a71_1 \n", + " rich conda-forge/noarch::rich-13.7.1-pyhd8ed1ab_0 \n", + " rich-click conda-forge/noarch::rich-click-1.7.4-pyhd8ed1ab_0 \n", + " scikit-learn conda-forge/linux-64::scikit-learn-1.2.2-py310hf7d194e_2 \n", + " scipy conda-forge/linux-64::scipy-1.13.0-py310hb13e2d6_0 \n", + " seaborn conda-forge/noarch::seaborn-0.13.2-hd8ed1ab_0 \n", + " seaborn-base conda-forge/noarch::seaborn-base-0.13.2-pyhd8ed1ab_0 \n", + " six conda-forge/noarch::six-1.16.0-pyh6c4a22f_0 \n", + " sox conda-forge/linux-64::sox-14.4.2-ha5cc309_1018 \n", + " soxr conda-forge/linux-64::soxr-0.1.3-h0b41bf4_3 \n", + " soxr-python conda-forge/linux-64::soxr-python-0.3.7-py310h1f7b6fc_0 \n", + " sqlalchemy conda-forge/linux-64::sqlalchemy-2.0.29-py310h2372a71_0 \n", + " sqlite conda-forge/linux-64::sqlite-3.44.2-h2c6b66d_0 \n", + " statsmodels conda-forge/linux-64::statsmodels-0.14.1-py310h1f7b6fc_0 \n", + " svt-av1 conda-forge/linux-64::svt-av1-1.8.0-h59595ed_0 \n", + " threadpoolctl conda-forge/noarch::threadpoolctl-3.4.0-pyhc1e730c_0 \n", + " typing-extensions conda-forge/noarch::typing-extensions-4.11.0-hd8ed1ab_0 \n", + " typing_extensions conda-forge/noarch::typing_extensions-4.11.0-pyha770c72_0 \n", + " tzcode conda-forge/linux-64::tzcode-2024a-h3f72095_0 \n", + " unicodedata2 conda-forge/linux-64::unicodedata2-15.1.0-py310h2372a71_0 \n", + " x264 conda-forge/linux-64::x264-1!164.3095-h166bdaf_2 \n", + " x265 conda-forge/linux-64::x265-3.5-h924138e_3 \n", + " xorg-fixesproto conda-forge/linux-64::xorg-fixesproto-5.0-h7f98852_1002 \n", + " xorg-kbproto conda-forge/linux-64::xorg-kbproto-1.0.7-h7f98852_1002 \n", + " xorg-libice conda-forge/linux-64::xorg-libice-1.1.1-hd590300_0 \n", + " xorg-libsm conda-forge/linux-64::xorg-libsm-1.2.4-h7391055_0 \n", + " xorg-libx11 conda-forge/linux-64::xorg-libx11-1.8.9-h8ee46fc_0 \n", + " xorg-libxau conda-forge/linux-64::xorg-libxau-1.0.11-hd590300_0 \n", + " xorg-libxdmcp conda-forge/linux-64::xorg-libxdmcp-1.1.3-h7f98852_0 \n", + " xorg-libxext conda-forge/linux-64::xorg-libxext-1.3.4-h0b41bf4_2 \n", + " xorg-libxfixes conda-forge/linux-64::xorg-libxfixes-5.0.3-h7f98852_1004 \n", + " xorg-libxrender conda-forge/linux-64::xorg-libxrender-0.9.11-hd590300_0 \n", + " xorg-renderproto conda-forge/linux-64::xorg-renderproto-0.11.1-h7f98852_1002 \n", + " xorg-xextproto conda-forge/linux-64::xorg-xextproto-7.3.0-h0b41bf4_1003 \n", + " xorg-xproto conda-forge/linux-64::xorg-xproto-7.0.31-h7f98852_1007 \n", + " yaml conda-forge/linux-64::yaml-0.2.5-h7f98852_2 \n", + " zipp conda-forge/noarch::zipp-3.17.0-pyhd8ed1ab_0 \n", + " zlib conda-forge/linux-64::zlib-1.2.13-hd590300_5 \n", + "\n", + "The following packages will be UPDATED:\n", + "\n", + " ca-certificates 2023.11.17-hbcca054_0 --> 2024.2.2-hbcca054_0 \n", + " certifi 2023.11.17-pyhd8ed1ab_0 --> 2024.2.2-pyhd8ed1ab_0 \n", + " openssl 3.2.0-hd590300_1 --> 3.2.1-hd590300_1 \n", + "\n", + "\n", + "\n", + "Downloading and Extracting Packages:\n", + "cudatoolkit-11.8.0 | 682.5 MB | : 0% 0/1 [00:00torch==2.1.0)\n", + " Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", + "Collecting MarkupSafe>=2.0 (from jinja2->torch==2.1.0)\n", + " Downloading MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.0 kB)\n", + "Collecting mpmath>=0.19 (from sympy->torch==2.1.0)\n", + " Downloading mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)\n", + "Downloading torch-2.1.0-cp310-cp310-manylinux1_x86_64.whl (670.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m670.2/670.2 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_nccl_cu12-2.18.1-py3-none-manylinux1_x86_64.whl (209.8 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m209.8/209.8 MB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading triton-2.1.0-0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (89.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m89.2/89.2 MB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading filelock-3.13.4-py3-none-any.whl (11 kB)\n", + "Downloading fsspec-2024.3.1-py3-none-any.whl (171 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m172.0/172.0 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading Jinja2-3.1.3-py3-none-any.whl (133 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.2/133.2 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading networkx-3.3-py3-none-any.whl (1.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading sympy-1.12-py3-none-any.whl (5.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.7/5.7 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)\n", + "Downloading mpmath-1.3.0-py3-none-any.whl (536 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.2/536.2 kB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: mpmath, sympy, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, networkx, MarkupSafe, fsspec, filelock, triton, nvidia-cusparse-cu12, nvidia-cudnn-cu12, jinja2, nvidia-cusolver-cu12, torch\n", + "Successfully installed MarkupSafe-2.1.5 filelock-3.13.4 fsspec-2024.3.1 jinja2-3.1.3 mpmath-1.3.0 networkx-3.3 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.18.1 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105 sympy-1.12 torch-2.1.0 triton-2.1.0\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCollecting tensorboard==2.16.2\n", + " Downloading tensorboard-2.16.2-py3-none-any.whl.metadata (1.6 kB)\n", + "Collecting absl-py>=0.4 (from tensorboard==2.16.2)\n", + " Downloading absl_py-2.1.0-py3-none-any.whl.metadata (2.3 kB)\n", + "Collecting grpcio>=1.48.2 (from tensorboard==2.16.2)\n", + " Downloading grpcio-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)\n", + "Collecting markdown>=2.6.8 (from tensorboard==2.16.2)\n", + " Downloading Markdown-3.6-py3-none-any.whl.metadata (7.0 kB)\n", + "Requirement already satisfied: numpy>=1.12.0 in /usr/local/lib/python3.10/site-packages (from tensorboard==2.16.2) (1.26.4)\n", + "Collecting protobuf!=4.24.0,>=3.19.6 (from tensorboard==2.16.2)\n", + " Downloading protobuf-5.26.1-cp37-abi3-manylinux2014_x86_64.whl.metadata (592 bytes)\n", + "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/site-packages (from tensorboard==2.16.2) (68.2.2)\n", + "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/site-packages (from tensorboard==2.16.2) (1.16.0)\n", + "Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard==2.16.2)\n", + " Downloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl.metadata (1.1 kB)\n", + "Collecting werkzeug>=1.0.1 (from tensorboard==2.16.2)\n", + " Downloading werkzeug-3.0.2-py3-none-any.whl.metadata (4.1 kB)\n", + "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/site-packages (from werkzeug>=1.0.1->tensorboard==2.16.2) (2.1.5)\n", + "Downloading tensorboard-2.16.2-py3-none-any.whl (5.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m22.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading absl_py-2.1.0-py3-none-any.whl (133 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.7/133.7 kB\u001b[0m \u001b[31m12.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading grpcio-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m58.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading Markdown-3.6-py3-none-any.whl (105 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.4/105.4 kB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading protobuf-5.26.1-cp37-abi3-manylinux2014_x86_64.whl (302 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.8/302.8 kB\u001b[0m \u001b[31m24.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl (6.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.6/6.6 MB\u001b[0m \u001b[31m63.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading werkzeug-3.0.2-py3-none-any.whl (226 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m226.8/226.8 kB\u001b[0m \u001b[31m20.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: werkzeug, tensorboard-data-server, protobuf, markdown, grpcio, absl-py, tensorboard\n", + "Successfully installed absl-py-2.1.0 grpcio-1.62.1 markdown-3.6 protobuf-5.26.1 tensorboard-2.16.2 tensorboard-data-server-0.7.2 werkzeug-3.0.2\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCollecting phonemizer==3.2.1\n", + " Downloading phonemizer-3.2.1-py3-none-any.whl.metadata (7.4 kB)\n", + "Requirement already satisfied: joblib in /usr/local/lib/python3.10/site-packages (from phonemizer==3.2.1) (1.4.0)\n", + "Collecting segments (from phonemizer==3.2.1)\n", + " Downloading segments-2.2.1-py2.py3-none-any.whl.metadata (3.3 kB)\n", + "Collecting attrs>=18.1 (from phonemizer==3.2.1)\n", + " Downloading attrs-23.2.0-py3-none-any.whl.metadata (9.5 kB)\n", + "Collecting dlinfo (from phonemizer==3.2.1)\n", + " Downloading dlinfo-1.2.1-py3-none-any.whl.metadata (1.1 kB)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from phonemizer==3.2.1) (4.11.0)\n", + "Collecting clldutils>=1.7.3 (from segments->phonemizer==3.2.1)\n", + " Downloading clldutils-3.22.2-py2.py3-none-any.whl.metadata (3.0 kB)\n", + "Collecting csvw>=1.5.6 (from segments->phonemizer==3.2.1)\n", + " Downloading csvw-3.3.0-py2.py3-none-any.whl.metadata (10 kB)\n", + "Collecting regex (from segments->phonemizer==3.2.1)\n", + " Downloading regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m1.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: python-dateutil in /usr/local/lib/python3.10/site-packages (from clldutils>=1.7.3->segments->phonemizer==3.2.1) (2.9.0)\n", + "Collecting tabulate>=0.7.7 (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", + " Downloading tabulate-0.9.0-py3-none-any.whl.metadata (34 kB)\n", + "Collecting colorlog (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", + " Downloading colorlog-6.8.2-py3-none-any.whl.metadata (10 kB)\n", + "Collecting bibtexparser>=2.0.0b4 (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", + " Downloading bibtexparser-2.0.0b7-py3-none-any.whl.metadata (5.6 kB)\n", + "Collecting pylatexenc (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", + " Downloading pylatexenc-2.10.tar.gz (162 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m162.6/162.6 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: markdown in /usr/local/lib/python3.10/site-packages (from clldutils>=1.7.3->segments->phonemizer==3.2.1) (3.6)\n", + "Collecting lxml (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", + " Downloading lxml-5.2.1-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.4 kB)\n", + "Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/site-packages (from clldutils>=1.7.3->segments->phonemizer==3.2.1) (2.1.5)\n", + "Collecting babel (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading Babel-2.14.0-py3-none-any.whl.metadata (1.6 kB)\n", + "Requirement already satisfied: colorama in /usr/local/lib/python3.10/site-packages (from csvw>=1.5.6->segments->phonemizer==3.2.1) (0.4.6)\n", + "Collecting isodate (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading isodate-0.6.1-py2.py3-none-any.whl.metadata (9.6 kB)\n", + "Collecting jsonschema (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading jsonschema-4.21.1-py3-none-any.whl.metadata (7.8 kB)\n", + "Collecting language-tags (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading language_tags-1.2.0-py3-none-any.whl.metadata (2.1 kB)\n", + "Collecting rdflib (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading rdflib-7.0.0-py3-none-any.whl.metadata (11 kB)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/site-packages (from csvw>=1.5.6->segments->phonemizer==3.2.1) (2.31.0)\n", + "Collecting rfc3986<2 (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading rfc3986-1.5.0-py2.py3-none-any.whl.metadata (6.5 kB)\n", + "Collecting uritemplate>=3.0.0 (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading uritemplate-4.1.1-py2.py3-none-any.whl.metadata (2.9 kB)\n", + "Requirement already satisfied: six in /usr/local/lib/python3.10/site-packages (from isodate->csvw>=1.5.6->segments->phonemizer==3.2.1) (1.16.0)\n", + "Collecting jsonschema-specifications>=2023.03.6 (from jsonschema->csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading jsonschema_specifications-2023.12.1-py3-none-any.whl.metadata (3.0 kB)\n", + "Collecting referencing>=0.28.4 (from jsonschema->csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading referencing-0.34.0-py3-none-any.whl.metadata (2.8 kB)\n", + "Collecting rpds-py>=0.7.1 (from jsonschema->csvw>=1.5.6->segments->phonemizer==3.2.1)\n", + " Downloading rpds_py-0.18.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.1 kB)\n", + "Requirement already satisfied: pyparsing<4,>=2.1.0 in /usr/local/lib/python3.10/site-packages (from rdflib->csvw>=1.5.6->segments->phonemizer==3.2.1) (3.1.2)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (2.1.0)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (2024.2.2)\n", + "Downloading phonemizer-3.2.1-py3-none-any.whl (90 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.6/90.6 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading attrs-23.2.0-py3-none-any.whl (60 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading dlinfo-1.2.1-py3-none-any.whl (3.6 kB)\n", + "Downloading segments-2.2.1-py2.py3-none-any.whl (15 kB)\n", + "Downloading clldutils-3.22.2-py2.py3-none-any.whl (1.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m15.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading csvw-3.3.0-py2.py3-none-any.whl (57 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.8/57.8 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (773 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m774.0/774.0 kB\u001b[0m \u001b[31m36.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading bibtexparser-2.0.0b7-py3-none-any.whl (38 kB)\n", + "Downloading rfc3986-1.5.0-py2.py3-none-any.whl (31 kB)\n", + "Downloading tabulate-0.9.0-py3-none-any.whl (35 kB)\n", + "Downloading uritemplate-4.1.1-py2.py3-none-any.whl (10 kB)\n", + "Downloading Babel-2.14.0-py3-none-any.whl (11.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.0/11.0 MB\u001b[0m \u001b[31m56.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading colorlog-6.8.2-py3-none-any.whl (11 kB)\n", + "Downloading isodate-0.6.1-py2.py3-none-any.whl (41 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.7/41.7 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading jsonschema-4.21.1-py3-none-any.whl (85 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.5/85.5 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading language_tags-1.2.0-py3-none-any.whl (213 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m213.4/213.4 kB\u001b[0m \u001b[31m19.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading lxml-5.2.1-cp310-cp310-manylinux_2_28_x86_64.whl (5.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.0/5.0 MB\u001b[0m \u001b[31m56.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading rdflib-7.0.0-py3-none-any.whl (531 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m531.9/531.9 kB\u001b[0m \u001b[31m42.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading jsonschema_specifications-2023.12.1-py3-none-any.whl (18 kB)\n", + "Downloading referencing-0.34.0-py3-none-any.whl (26 kB)\n", + "Downloading rpds_py-0.18.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m53.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hBuilding wheels for collected packages: pylatexenc\n", + " Building wheel for pylatexenc (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for pylatexenc: filename=pylatexenc-2.10-py3-none-any.whl size=136816 sha256=4c57cdcfd98c0a2de7a749fe90c9917f37213c2cd8423e01aeddd6a5b5438202\n", + " Stored in directory: /root/.cache/pip/wheels/d3/31/8b/e09b0386afd80cfc556c00408c9aeea5c35c4d484a9c762fd5\n", + "Successfully built pylatexenc\n", + "Installing collected packages: rfc3986, pylatexenc, language-tags, dlinfo, uritemplate, tabulate, rpds-py, regex, lxml, isodate, colorlog, bibtexparser, babel, attrs, referencing, rdflib, clldutils, jsonschema-specifications, jsonschema, csvw, segments, phonemizer\n", + "Successfully installed attrs-23.2.0 babel-2.14.0 bibtexparser-2.0.0b7 clldutils-3.22.2 colorlog-6.8.2 csvw-3.3.0 dlinfo-1.2.1 isodate-0.6.1 jsonschema-4.21.1 jsonschema-specifications-2023.12.1 language-tags-1.2.0 lxml-5.2.1 phonemizer-3.2.1 pylatexenc-2.10 rdflib-7.0.0 referencing-0.34.0 regex-2024.4.16 rfc3986-1.5.0 rpds-py-0.18.0 segments-2.2.1 tabulate-0.9.0 uritemplate-4.1.1\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCollecting torchaudio==2.1.0\n", + " Downloading torchaudio-2.1.0-cp310-cp310-manylinux1_x86_64.whl.metadata (5.7 kB)\n", + "Requirement already satisfied: torch==2.1.0 in /usr/local/lib/python3.10/site-packages (from torchaudio==2.1.0) (2.1.0)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (3.13.4)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (4.11.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (2024.3.1)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (2.18.1)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", + "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (2.1.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.1.0->torchaudio==2.1.0) (12.4.127)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/site-packages (from jinja2->torch==2.1.0->torchaudio==2.1.0) (2.1.5)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch==2.1.0->torchaudio==2.1.0) (1.3.0)\n", + "Downloading torchaudio-2.1.0-cp310-cp310-manylinux1_x86_64.whl (3.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.3/3.3 MB\u001b[0m \u001b[31m14.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: torchaudio\n", + "Successfully installed torchaudio-2.1.0\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCollecting datasets==2.16.0\n", + " Downloading datasets-2.16.0-py3-none-any.whl.metadata (20 kB)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (3.13.4)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (1.26.4)\n", + "Collecting pyarrow>=8.0.0 (from datasets==2.16.0)\n", + " Downloading pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\n", + "Collecting pyarrow-hotfix (from datasets==2.16.0)\n", + " Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n", + "Collecting dill<0.3.8,>=0.3.0 (from datasets==2.16.0)\n", + " Downloading dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)\n", + "Requirement already satisfied: pandas in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (2.2.2)\n", + "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (2.31.0)\n", + "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (4.66.1)\n", + "Collecting xxhash (from datasets==2.16.0)\n", + " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n", + "Collecting multiprocess (from datasets==2.16.0)\n", + " Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n", + "Collecting fsspec<=2023.10.0,>=2023.1.0 (from fsspec[http]<=2023.10.0,>=2023.1.0->datasets==2.16.0)\n", + " Downloading fsspec-2023.10.0-py3-none-any.whl.metadata (6.8 kB)\n", + "Collecting aiohttp (from datasets==2.16.0)\n", + " Downloading aiohttp-3.9.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.5 kB)\n", + "Collecting huggingface-hub>=0.19.4 (from datasets==2.16.0)\n", + " Downloading huggingface_hub-0.22.2-py3-none-any.whl.metadata (12 kB)\n", + "Requirement already satisfied: packaging in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (23.2)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (6.0.1)\n", + "Collecting aiosignal>=1.1.2 (from aiohttp->datasets==2.16.0)\n", + " Downloading aiosignal-1.3.1-py3-none-any.whl.metadata (4.0 kB)\n", + "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/site-packages (from aiohttp->datasets==2.16.0) (23.2.0)\n", + "Collecting frozenlist>=1.1.1 (from aiohttp->datasets==2.16.0)\n", + " Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n", + "Collecting multidict<7.0,>=4.5 (from aiohttp->datasets==2.16.0)\n", + " Downloading multidict-6.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.2 kB)\n", + "Collecting yarl<2.0,>=1.0 (from aiohttp->datasets==2.16.0)\n", + " Downloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (31 kB)\n", + "Collecting async-timeout<5.0,>=4.0 (from aiohttp->datasets==2.16.0)\n", + " Downloading async_timeout-4.0.3-py3-none-any.whl.metadata (4.2 kB)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/site-packages (from huggingface-hub>=0.19.4->datasets==2.16.0) (4.11.0)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (2.1.0)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (2024.2.2)\n", + "INFO: pip is looking at multiple versions of multiprocess to determine which version is compatible with other requirements. This could take a while.\n", + "Collecting multiprocess (from datasets==2.16.0)\n", + " Downloading multiprocess-0.70.15-py310-none-any.whl.metadata (7.2 kB)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/site-packages (from pandas->datasets==2.16.0) (2.9.0)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/site-packages (from pandas->datasets==2.16.0) (2024.1)\n", + "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/site-packages (from pandas->datasets==2.16.0) (2024.1)\n", + "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas->datasets==2.16.0) (1.16.0)\n", + "Downloading datasets-2.16.0-py3-none-any.whl (507 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading dill-0.3.7-py3-none-any.whl (115 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading fsspec-2023.10.0-py3-none-any.whl (166 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.4/166.4 kB\u001b[0m \u001b[31m14.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading aiohttp-3.9.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m19.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading huggingface_hub-0.22.2-py3-none-any.whl (388 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m388.9/388.9 kB\u001b[0m \u001b[31m31.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl (38.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m24.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n", + "Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m17.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n", + "Downloading async_timeout-4.0.3-py3-none-any.whl (5.7 kB)\n", + "Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (239 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m239.5/239.5 kB\u001b[0m \u001b[31m20.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading multidict-6.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (124 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.3/124.3 kB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (301 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m301.6/301.6 kB\u001b[0m \u001b[31m25.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: xxhash, pyarrow-hotfix, pyarrow, multidict, fsspec, frozenlist, dill, async-timeout, yarl, multiprocess, huggingface-hub, aiosignal, aiohttp, datasets\n", + " Attempting uninstall: fsspec\n", + " Found existing installation: fsspec 2024.3.1\n", + " Uninstalling fsspec-2024.3.1:\n", + " Successfully uninstalled fsspec-2024.3.1\n", + "Successfully installed aiohttp-3.9.5 aiosignal-1.3.1 async-timeout-4.0.3 datasets-2.16.0 dill-0.3.7 frozenlist-1.4.1 fsspec-2023.10.0 huggingface-hub-0.22.2 multidict-6.0.5 multiprocess-0.70.15 pyarrow-15.0.2 pyarrow-hotfix-0.6 xxhash-3.4.1 yarl-1.9.4\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCollecting torchmetrics==0.11.1\n", + " Downloading torchmetrics-0.11.1-py3-none-any.whl.metadata (16 kB)\n", + "Requirement already satisfied: numpy>=1.17.2 in /usr/local/lib/python3.10/site-packages (from torchmetrics==0.11.1) (1.26.4)\n", + "Requirement already satisfied: torch>=1.8.1 in /usr/local/lib/python3.10/site-packages (from torchmetrics==0.11.1) (2.1.0)\n", + "Requirement already satisfied: packaging in /usr/local/lib/python3.10/site-packages (from torchmetrics==0.11.1) (23.2)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (3.13.4)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (4.11.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (2023.10.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (2.18.1)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", + "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (2.1.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.8.1->torchmetrics==0.11.1) (12.4.127)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/site-packages (from jinja2->torch>=1.8.1->torchmetrics==0.11.1) (2.1.5)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch>=1.8.1->torchmetrics==0.11.1) (1.3.0)\n", + "Downloading torchmetrics-0.11.1-py3-none-any.whl (517 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m517.2/517.2 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: torchmetrics\n", + "Successfully installed torchmetrics-0.11.1\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCollecting torchvision==0.16.0\n", + " Downloading torchvision-0.16.0-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n", + "Requirement already satisfied: numpy in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (1.26.4)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (2.31.0)\n", + "Requirement already satisfied: torch==2.1.0 in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (2.1.0)\n", + "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (10.3.0)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (3.13.4)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (4.11.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (2023.10.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (2.18.1)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", + "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (2.1.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.1.0->torchvision==0.16.0) (12.4.127)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (2.1.0)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (2024.2.2)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/site-packages (from jinja2->torch==2.1.0->torchvision==0.16.0) (2.1.5)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch==2.1.0->torchvision==0.16.0) (1.3.0)\n", + "Downloading torchvision-0.16.0-cp310-cp310-manylinux1_x86_64.whl (6.9 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m22.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: torchvision\n", + "Successfully installed torchvision-0.16.0\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCollecting audiocraft\n", + " Cloning https://****@github.com/facebookresearch/audiocraft to /tmp/pip-install-kthaw99y/audiocraft_35cc3991adfe4664939ef82eecd3e7a1\n", + " Running command git clone --filter=blob:none --quiet 'https://****@github.com/facebookresearch/audiocraft' /tmp/pip-install-kthaw99y/audiocraft_35cc3991adfe4664939ef82eecd3e7a1\n", + " Resolved https://****@github.com/facebookresearch/audiocraft to commit 69fea8b290ad1b4b40d28f92d1dfc0ab01dbab85\n", + " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting av (from audiocraft)\n", + " Downloading av-12.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.6 kB)\n", + "Collecting einops (from audiocraft)\n", + " Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)\n", + "Collecting flashy>=0.0.1 (from audiocraft)\n", + " Downloading flashy-0.0.2.tar.gz (72 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.4/72.4 kB\u001b[0m \u001b[31m1.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting hydra-core>=1.1 (from audiocraft)\n", + " Downloading hydra_core-1.3.2-py3-none-any.whl.metadata (5.5 kB)\n", + "Collecting hydra_colorlog (from audiocraft)\n", + " Downloading hydra_colorlog-1.2.0-py3-none-any.whl.metadata (949 bytes)\n", + "Collecting julius (from audiocraft)\n", + " Downloading julius-0.2.7.tar.gz (59 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.6/59.6 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting num2words (from audiocraft)\n", + " Downloading num2words-0.5.13-py3-none-any.whl.metadata (12 kB)\n", + "Requirement already satisfied: numpy in /usr/local/lib/python3.10/site-packages (from audiocraft) (1.26.4)\n", + "Collecting sentencepiece (from audiocraft)\n", + " Downloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.7 kB)\n", + "Collecting spacy>=3.6.1 (from audiocraft)\n", + " Downloading spacy-3.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (27 kB)\n", + "Requirement already satisfied: torch==2.1.0 in /usr/local/lib/python3.10/site-packages (from audiocraft) (2.1.0)\n", + "Requirement already satisfied: torchaudio<2.1.2,>=2.0.0 in /usr/local/lib/python3.10/site-packages (from audiocraft) (2.1.0)\n", + "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/site-packages (from audiocraft) (0.22.2)\n", + "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/site-packages (from audiocraft) (4.66.1)\n", + "Collecting transformers>=4.31.0 (from audiocraft)\n", + " Downloading transformers-4.39.3-py3-none-any.whl.metadata (134 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m3.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting xformers<0.0.23 (from audiocraft)\n", + " Downloading xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl.metadata (1.0 kB)\n", + "Collecting demucs (from audiocraft)\n", + " Downloading demucs-4.0.1.tar.gz (1.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m14.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: librosa in /usr/local/lib/python3.10/site-packages (from audiocraft) (0.10.1)\n", + "Collecting gradio (from audiocraft)\n", + " Downloading gradio-4.26.0-py3-none-any.whl.metadata (15 kB)\n", + "Requirement already satisfied: torchmetrics in /usr/local/lib/python3.10/site-packages (from audiocraft) (0.11.1)\n", + "Collecting encodec (from audiocraft)\n", + " Downloading encodec-0.1.1.tar.gz (3.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.7/3.7 MB\u001b[0m \u001b[31m43.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/site-packages (from audiocraft) (5.26.1)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (3.13.4)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (4.11.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (2023.10.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (2.18.1)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", + "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (2.1.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.1.0->audiocraft) (12.4.127)\n", + "Collecting dora-search (from flashy>=0.0.1->audiocraft)\n", + " Downloading dora_search-0.1.12.tar.gz (87 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.1/87.1 kB\u001b[0m \u001b[31m8.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: colorlog in /usr/local/lib/python3.10/site-packages (from flashy>=0.0.1->audiocraft) (6.8.2)\n", + "Collecting omegaconf<2.4,>=2.2 (from hydra-core>=1.1->audiocraft)\n", + " Downloading omegaconf-2.3.0-py3-none-any.whl.metadata (3.9 kB)\n", + "Collecting antlr4-python3-runtime==4.9.* (from hydra-core>=1.1->audiocraft)\n", + " Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.0/117.0 kB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: packaging in /usr/local/lib/python3.10/site-packages (from hydra-core>=1.1->audiocraft) (23.2)\n", + "Collecting spacy-legacy<3.1.0,>=3.0.11 (from spacy>=3.6.1->audiocraft)\n", + " Downloading spacy_legacy-3.0.12-py2.py3-none-any.whl.metadata (2.8 kB)\n", + "Collecting spacy-loggers<2.0.0,>=1.0.0 (from spacy>=3.6.1->audiocraft)\n", + " Downloading spacy_loggers-1.0.5-py3-none-any.whl.metadata (23 kB)\n", + "Collecting murmurhash<1.1.0,>=0.28.0 (from spacy>=3.6.1->audiocraft)\n", + " Downloading murmurhash-1.0.10-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.0 kB)\n", + "Collecting cymem<2.1.0,>=2.0.2 (from spacy>=3.6.1->audiocraft)\n", + " Downloading cymem-2.0.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (8.4 kB)\n", + "Collecting preshed<3.1.0,>=3.0.2 (from spacy>=3.6.1->audiocraft)\n", + " Downloading preshed-3.0.9-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.2 kB)\n", + "Collecting thinc<8.3.0,>=8.2.2 (from spacy>=3.6.1->audiocraft)\n", + " Downloading thinc-8.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (15 kB)\n", + "Collecting wasabi<1.2.0,>=0.9.1 (from spacy>=3.6.1->audiocraft)\n", + " Downloading wasabi-1.1.2-py3-none-any.whl.metadata (28 kB)\n", + "Collecting srsly<3.0.0,>=2.4.3 (from spacy>=3.6.1->audiocraft)\n", + " Downloading srsly-2.4.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (20 kB)\n", + "Collecting catalogue<2.1.0,>=2.0.6 (from spacy>=3.6.1->audiocraft)\n", + " Downloading catalogue-2.0.10-py3-none-any.whl.metadata (14 kB)\n", + "Collecting weasel<0.4.0,>=0.1.0 (from spacy>=3.6.1->audiocraft)\n", + " Downloading weasel-0.3.4-py3-none-any.whl.metadata (4.7 kB)\n", + "Collecting typer<0.10.0,>=0.3.0 (from spacy>=3.6.1->audiocraft)\n", + " Downloading typer-0.9.4-py3-none-any.whl.metadata (14 kB)\n", + "Collecting smart-open<7.0.0,>=5.2.1 (from spacy>=3.6.1->audiocraft)\n", + " Downloading smart_open-6.4.0-py3-none-any.whl.metadata (21 kB)\n", + "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/site-packages (from spacy>=3.6.1->audiocraft) (2.31.0)\n", + "Collecting pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 (from spacy>=3.6.1->audiocraft)\n", + " Downloading pydantic-2.7.0-py3-none-any.whl.metadata (103 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m103.4/103.4 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: setuptools in /usr/local/lib/python3.10/site-packages (from spacy>=3.6.1->audiocraft) (68.2.2)\n", + "Collecting langcodes<4.0.0,>=3.2.0 (from spacy>=3.6.1->audiocraft)\n", + " Downloading langcodes-3.3.0-py3-none-any.whl.metadata (29 kB)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/site-packages (from transformers>=4.31.0->audiocraft) (6.0.1)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/site-packages (from transformers>=4.31.0->audiocraft) (2024.4.16)\n", + "Collecting tokenizers<0.19,>=0.14 (from transformers>=4.31.0->audiocraft)\n", + " Downloading tokenizers-0.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n", + "Collecting safetensors>=0.4.1 (from transformers>=4.31.0->audiocraft)\n", + " Downloading safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n", + "Collecting lameenc>=1.2 (from demucs->audiocraft)\n", + " Downloading lameenc-1.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl.metadata (803 bytes)\n", + "Collecting openunmix (from demucs->audiocraft)\n", + " Downloading openunmix-1.3.0-py3-none-any.whl.metadata (17 kB)\n", + "Collecting aiofiles<24.0,>=22.0 (from gradio->audiocraft)\n", + " Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)\n", + "Collecting altair<6.0,>=4.2.0 (from gradio->audiocraft)\n", + " Downloading altair-5.3.0-py3-none-any.whl.metadata (9.2 kB)\n", + "Collecting fastapi (from gradio->audiocraft)\n", + " Downloading fastapi-0.110.1-py3-none-any.whl.metadata (24 kB)\n", + "Collecting ffmpy (from gradio->audiocraft)\n", + " Downloading ffmpy-0.3.2.tar.gz (5.5 kB)\n", + " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting gradio-client==0.15.1 (from gradio->audiocraft)\n", + " Downloading gradio_client-0.15.1-py3-none-any.whl.metadata (7.1 kB)\n", + "Collecting httpx>=0.24.1 (from gradio->audiocraft)\n", + " Downloading httpx-0.27.0-py3-none-any.whl.metadata (7.2 kB)\n", + "Collecting importlib-resources<7.0,>=1.3 (from gradio->audiocraft)\n", + " Downloading importlib_resources-6.4.0-py3-none-any.whl.metadata (3.9 kB)\n", + "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (2.1.5)\n", + "Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (3.8.4)\n", + "Collecting orjson~=3.0 (from gradio->audiocraft)\n", + " Downloading orjson-3.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (49 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.7/49.7 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (2.2.2)\n", + "Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (10.3.0)\n", + "Collecting pydub (from gradio->audiocraft)\n", + " Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n", + "Collecting python-multipart>=0.0.9 (from gradio->audiocraft)\n", + " Downloading python_multipart-0.0.9-py3-none-any.whl.metadata (2.5 kB)\n", + "Collecting ruff>=0.2.2 (from gradio->audiocraft)\n", + " Downloading ruff-0.3.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (23 kB)\n", + "Collecting semantic-version~=2.0 (from gradio->audiocraft)\n", + " Downloading semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n", + "Collecting tomlkit==0.12.0 (from gradio->audiocraft)\n", + " Downloading tomlkit-0.12.0-py3-none-any.whl.metadata (2.7 kB)\n", + "Collecting uvicorn>=0.14.0 (from gradio->audiocraft)\n", + " Downloading uvicorn-0.29.0-py3-none-any.whl.metadata (6.3 kB)\n", + "Collecting websockets<12.0,>=10.0 (from gradio-client==0.15.1->gradio->audiocraft)\n", + " Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)\n", + "Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (3.0.1)\n", + "Requirement already satisfied: scipy>=1.2.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.13.0)\n", + "Requirement already satisfied: scikit-learn>=0.20.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.2.2)\n", + "Requirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.4.0)\n", + "Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (5.1.1)\n", + "Requirement already satisfied: numba>=0.51.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.59.1)\n", + "Requirement already satisfied: soundfile>=0.12.1 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.12.1)\n", + "Requirement already satisfied: pooch>=1.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.8.1)\n", + "Requirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.3.7)\n", + "Requirement already satisfied: lazy-loader>=0.1 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.4)\n", + "Requirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.0.7)\n", + "Collecting docopt>=0.6.2 (from num2words->audiocraft)\n", + " Downloading docopt-0.6.2.tar.gz (25 kB)\n", + " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/site-packages (from altair<6.0,>=4.2.0->gradio->audiocraft) (4.21.1)\n", + "Collecting toolz (from altair<6.0,>=4.2.0->gradio->audiocraft)\n", + " Downloading toolz-0.12.1-py3-none-any.whl.metadata (5.1 kB)\n", + "Collecting anyio (from httpx>=0.24.1->gradio->audiocraft)\n", + " Downloading anyio-4.3.0-py3-none-any.whl.metadata (4.6 kB)\n", + "Requirement already satisfied: certifi in /usr/local/lib/python3.10/site-packages (from httpx>=0.24.1->gradio->audiocraft) (2024.2.2)\n", + "Collecting httpcore==1.* (from httpx>=0.24.1->gradio->audiocraft)\n", + " Downloading httpcore-1.0.5-py3-none-any.whl.metadata (20 kB)\n", + "Requirement already satisfied: idna in /usr/local/lib/python3.10/site-packages (from httpx>=0.24.1->gradio->audiocraft) (3.6)\n", + "Collecting sniffio (from httpx>=0.24.1->gradio->audiocraft)\n", + " Downloading sniffio-1.3.1-py3-none-any.whl.metadata (3.9 kB)\n", + "Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx>=0.24.1->gradio->audiocraft)\n", + " Downloading h11-0.14.0-py3-none-any.whl.metadata (8.2 kB)\n", + "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (1.2.1)\n", + "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (0.12.1)\n", + "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (4.51.0)\n", + "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (1.4.5)\n", + "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (3.1.2)\n", + "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (2.9.0)\n", + "Requirement already satisfied: llvmlite<0.43,>=0.42.0dev0 in /usr/local/lib/python3.10/site-packages (from numba>=0.51.0->librosa->audiocraft) (0.42.0)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/site-packages (from pandas<3.0,>=1.0->gradio->audiocraft) (2024.1)\n", + "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/site-packages (from pandas<3.0,>=1.0->gradio->audiocraft) (2024.1)\n", + "Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.10/site-packages (from pooch>=1.0->librosa->audiocraft) (4.1.0)\n", + "Collecting annotated-types>=0.4.0 (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.6.1->audiocraft)\n", + " Downloading annotated_types-0.6.0-py3-none-any.whl.metadata (12 kB)\n", + "Collecting pydantic-core==2.18.1 (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.6.1->audiocraft)\n", + " Downloading pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.5 kB)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy>=3.6.1->audiocraft) (3.3.2)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy>=3.6.1->audiocraft) (2.1.0)\n", + "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/site-packages (from scikit-learn>=0.20.0->librosa->audiocraft) (3.4.0)\n", + "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/site-packages (from soundfile>=0.12.1->librosa->audiocraft) (1.16.0)\n", + "Collecting blis<0.8.0,>=0.7.8 (from thinc<8.3.0,>=8.2.2->spacy>=3.6.1->audiocraft)\n", + " Downloading blis-0.7.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.4 kB)\n", + "Collecting confection<1.0.0,>=0.0.1 (from thinc<8.3.0,>=8.2.2->spacy>=3.6.1->audiocraft)\n", + " Downloading confection-0.1.4-py3-none-any.whl.metadata (19 kB)\n", + "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.10/site-packages (from typer<0.10.0,>=0.3.0->spacy>=3.6.1->audiocraft) (8.1.7)\n", + "Requirement already satisfied: colorama<0.5.0,>=0.4.3 in /usr/local/lib/python3.10/site-packages (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (0.4.6)\n", + "Collecting shellingham<2.0.0,>=1.3.0 (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft)\n", + " Downloading shellingham-1.5.4-py2.py3-none-any.whl.metadata (3.5 kB)\n", + "Requirement already satisfied: rich<14.0.0,>=10.11.0 in /usr/local/lib/python3.10/site-packages (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (13.7.1)\n", + "Collecting cloudpathlib<0.17.0,>=0.7.0 (from weasel<0.4.0,>=0.1.0->spacy>=3.6.1->audiocraft)\n", + " Downloading cloudpathlib-0.16.0-py3-none-any.whl.metadata (14 kB)\n", + "Collecting retrying (from dora-search->flashy>=0.0.1->audiocraft)\n", + " Downloading retrying-1.3.4-py3-none-any.whl.metadata (6.9 kB)\n", + "Collecting submitit (from dora-search->flashy>=0.0.1->audiocraft)\n", + " Downloading submitit-1.5.1-py3-none-any.whl.metadata (8.0 kB)\n", + "Collecting treetable (from dora-search->flashy>=0.0.1->audiocraft)\n", + " Downloading treetable-0.2.5.tar.gz (10 kB)\n", + " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting starlette<0.38.0,>=0.37.2 (from fastapi->gradio->audiocraft)\n", + " Downloading starlette-0.37.2-py3-none-any.whl.metadata (5.9 kB)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch==2.1.0->audiocraft) (1.3.0)\n", + "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/site-packages (from cffi>=1.0->soundfile>=0.12.1->librosa->audiocraft) (2.21)\n", + "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (23.2.0)\n", + "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (2023.12.1)\n", + "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (0.34.0)\n", + "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (0.18.0)\n", + "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio->audiocraft) (1.16.0)\n", + "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/site-packages (from rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (3.0.0)\n", + "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/site-packages (from rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (2.17.2)\n", + "Collecting exceptiongroup>=1.0.2 (from anyio->httpx>=0.24.1->gradio->audiocraft)\n", + " Downloading exceptiongroup-1.2.0-py3-none-any.whl.metadata (6.6 kB)\n", + "Collecting cloudpickle>=1.2.1 (from submitit->dora-search->flashy>=0.0.1->audiocraft)\n", + " Downloading cloudpickle-3.0.0-py3-none-any.whl.metadata (7.0 kB)\n", + "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/site-packages (from markdown-it-py>=2.2.0->rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (0.1.2)\n", + "Downloading hydra_core-1.3.2-py3-none-any.whl (154 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.5/154.5 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading spacy-3.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (6.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.6/6.6 MB\u001b[0m \u001b[31m49.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading transformers-4.39.3-py3-none-any.whl (8.8 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m67.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl (211.8 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.8/211.8 MB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading av-12.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (33.8 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m33.8/33.8 MB\u001b[0m \u001b[31m35.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading einops-0.7.0-py3-none-any.whl (44 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading gradio-4.26.0-py3-none-any.whl (17.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.1/17.1 MB\u001b[0m \u001b[31m49.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading gradio_client-0.15.1-py3-none-any.whl (313 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m313.6/313.6 kB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n", + "Downloading hydra_colorlog-1.2.0-py3-none-any.whl (3.6 kB)\n", + "Downloading num2words-0.5.13-py3-none-any.whl (143 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m143.3/143.3 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m51.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n", + "Downloading altair-5.3.0-py3-none-any.whl (857 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m857.8/857.8 kB\u001b[0m \u001b[31m43.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading catalogue-2.0.10-py3-none-any.whl (17 kB)\n", + "Downloading cymem-2.0.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (46 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.1/46.1 kB\u001b[0m \u001b[31m4.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading httpx-0.27.0-py3-none-any.whl (75 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m7.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading importlib_resources-6.4.0-py3-none-any.whl (38 kB)\n", + "Downloading lameenc-1.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl (239 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m239.8/239.8 kB\u001b[0m \u001b[31m21.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading langcodes-3.3.0-py3-none-any.whl (181 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m181.6/181.6 kB\u001b[0m \u001b[31m15.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading murmurhash-1.0.10-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (29 kB)\n", + "Downloading omegaconf-2.3.0-py3-none-any.whl (79 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.5/79.5 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading orjson-3.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (141 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m141.1/141.1 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading preshed-3.0.9-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (156 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m156.9/156.9 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading pydantic-2.7.0-py3-none-any.whl (407 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m407.9/407.9 kB\u001b[0m \u001b[31m32.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m54.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n", + "Downloading ruff-0.3.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.9 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.9/8.9 MB\u001b[0m \u001b[31m56.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m49.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n", + "Downloading smart_open-6.4.0-py3-none-any.whl (57 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.0/57.0 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading spacy_legacy-3.0.12-py2.py3-none-any.whl (29 kB)\n", + "Downloading spacy_loggers-1.0.5-py3-none-any.whl (22 kB)\n", + "Downloading srsly-2.4.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (493 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m493.0/493.0 kB\u001b[0m \u001b[31m29.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading thinc-8.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (922 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m922.3/922.3 kB\u001b[0m \u001b[31m46.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading tokenizers-0.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m54.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading typer-0.9.4-py3-none-any.whl (45 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading uvicorn-0.29.0-py3-none-any.whl (60 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading wasabi-1.1.2-py3-none-any.whl (27 kB)\n", + "Downloading weasel-0.3.4-py3-none-any.whl (50 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.1/50.1 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading fastapi-0.110.1-py3-none-any.whl (91 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.9/91.9 kB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading openunmix-1.3.0-py3-none-any.whl (40 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.0/40.0 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n", + "Downloading annotated_types-0.6.0-py3-none-any.whl (12 kB)\n", + "Downloading blis-0.7.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.2/10.2 MB\u001b[0m \u001b[31m54.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading cloudpathlib-0.16.0-py3-none-any.whl (45 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.0/45.0 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading confection-0.1.4-py3-none-any.whl (35 kB)\n", + "Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n", + "Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading anyio-4.3.0-py3-none-any.whl (85 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.6/85.6 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading sniffio-1.3.1-py3-none-any.whl (10 kB)\n", + "Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading retrying-1.3.4-py3-none-any.whl (11 kB)\n", + "Downloading submitit-1.5.1-py3-none-any.whl (74 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m74.7/74.7 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading toolz-0.12.1-py3-none-any.whl (56 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.1/56.1 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading cloudpickle-3.0.0-py3-none-any.whl (20 kB)\n", + "Downloading exceptiongroup-1.2.0-py3-none-any.whl (16 kB)\n", + "Building wheels for collected packages: audiocraft, flashy, antlr4-python3-runtime, demucs, julius, encodec, docopt, dora-search, ffmpy, treetable\n", + " Building wheel for audiocraft (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for audiocraft: filename=audiocraft-1.3.0a1-py3-none-any.whl size=264806 sha256=7a718f3484e2f14f82562388442c366616e7252ffda2824e4ea16ffe449601cb\n", + " Stored in directory: /tmp/pip-ephem-wheel-cache-7svi6_32/wheels/61/bb/15/cf53514254501b4472fb64d137bd3ab88737daf6917dfcbdc9\n", + " Building wheel for flashy (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for flashy: filename=flashy-0.0.2-py3-none-any.whl size=34527 sha256=c684f44a995181f7bf4d39852fd2961bc695a0dd8618116d2ddee969908fd23e\n", + " Stored in directory: /root/.cache/pip/wheels/07/bd/3d/16c6bc059203299f37b6014643b739afb7f6d1be13a94fc2f7\n", + " Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for antlr4-python3-runtime: filename=antlr4_python3_runtime-4.9.3-py3-none-any.whl size=144554 sha256=882304c91af3c0fe39ed685f7ee9a3142d860ada9311dd2512a5bf5289e4c764\n", + " Stored in directory: /root/.cache/pip/wheels/12/93/dd/1f6a127edc45659556564c5730f6d4e300888f4bca2d4c5a88\n", + " Building wheel for demucs (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for demucs: filename=demucs-4.0.1-py3-none-any.whl size=78391 sha256=9bf9cafaf6fbcf260534861b3513e131f3a1ba0bb5af6930af9ebe97783a2fb5\n", + " Stored in directory: /root/.cache/pip/wheels/2a/65/a1/6cc0e525a84375af3b09823b3326b0ece53c4e68302c054548\n", + " Building wheel for julius (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for julius: filename=julius-0.2.7-py3-none-any.whl size=21870 sha256=de9d763ebd7f85a5ad43ec67b005b190d336eded70e3b2afe487c62f278c5939\n", + " Stored in directory: /root/.cache/pip/wheels/b9/b2/05/f883527ffcb7f2ead5438a2c23439aa0c881eaa9a4c80256f4\n", + " Building wheel for encodec (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for encodec: filename=encodec-0.1.1-py3-none-any.whl size=45759 sha256=0af63d8afea5a09bacc48f6fa2767e53d732883c98e862d8904d608531bae959\n", + " Stored in directory: /root/.cache/pip/wheels/fc/36/cb/81af8b985a5f5e0815312d5e52b41263237af07b977e6bcbf3\n", + " Building wheel for docopt (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=61388c7fb75041fc6643e6a8638dd74b74bba5dbbb58484a48ffafcee94744ca\n", + " Stored in directory: /root/.cache/pip/wheels/fc/ab/d4/5da2067ac95b36618c629a5f93f809425700506f72c9732fac\n", + " Building wheel for dora-search (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for dora-search: filename=dora_search-0.1.12-py3-none-any.whl size=75093 sha256=f3392d966ef342611ed2a3ebdfcd5b17ef4659bac57a6848084af79a88665e54\n", + " Stored in directory: /root/.cache/pip/wheels/b1/c2/c0/bea5cc405497284d584b958f293ef32c23bad42ae5e44d973c\n", + " Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for ffmpy: filename=ffmpy-0.3.2-py3-none-any.whl size=5584 sha256=54a8e3c6638890205277f5d18ff56d1da1ed9147bc10b2a26eb32af1e7b860bb\n", + " Stored in directory: /root/.cache/pip/wheels/bd/65/9a/671fc6dcde07d4418df0c592f8df512b26d7a0029c2a23dd81\n", + " Building wheel for treetable (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for treetable: filename=treetable-0.2.5-py3-none-any.whl size=7333 sha256=51072008b023f976ac4932d447b9fdc088156bb7918ae05caada65a1fabbc9f5\n", + " Stored in directory: /root/.cache/pip/wheels/72/55/0e/91c3655bdb162446f8a7cd477579397544454a63ae7c599c0c\n", + "Successfully built audiocraft flashy antlr4-python3-runtime demucs julius encodec docopt dora-search ffmpy treetable\n", + "Installing collected packages: sentencepiece, pydub, lameenc, ffmpy, docopt, cymem, antlr4-python3-runtime, websockets, wasabi, typer, treetable, toolz, tomlkit, spacy-loggers, spacy-legacy, sniffio, smart-open, shellingham, semantic-version, safetensors, ruff, retrying, python-multipart, pydantic-core, orjson, omegaconf, num2words, murmurhash, langcodes, importlib-resources, h11, exceptiongroup, einops, cloudpickle, cloudpathlib, catalogue, blis, av, annotated-types, aiofiles, uvicorn, submitit, srsly, pydantic, preshed, hydra-core, httpcore, anyio, tokenizers, starlette, hydra_colorlog, httpx, confection, xformers, weasel, transformers, thinc, julius, gradio-client, fastapi, dora-search, altair, spacy, openunmix, gradio, flashy, encodec, demucs, audiocraft\n", + "Successfully installed aiofiles-23.2.1 altair-5.3.0 annotated-types-0.6.0 antlr4-python3-runtime-4.9.3 anyio-4.3.0 audiocraft-1.3.0a1 av-12.0.0 blis-0.7.11 catalogue-2.0.10 cloudpathlib-0.16.0 cloudpickle-3.0.0 confection-0.1.4 cymem-2.0.8 demucs-4.0.1 docopt-0.6.2 dora-search-0.1.12 einops-0.7.0 encodec-0.1.1 exceptiongroup-1.2.0 fastapi-0.110.1 ffmpy-0.3.2 flashy-0.0.2 gradio-4.26.0 gradio-client-0.15.1 h11-0.14.0 httpcore-1.0.5 httpx-0.27.0 hydra-core-1.3.2 hydra_colorlog-1.2.0 importlib-resources-6.4.0 julius-0.2.7 lameenc-1.7.0 langcodes-3.3.0 murmurhash-1.0.10 num2words-0.5.13 omegaconf-2.3.0 openunmix-1.3.0 orjson-3.10.1 preshed-3.0.9 pydantic-2.7.0 pydantic-core-2.18.1 pydub-0.25.1 python-multipart-0.0.9 retrying-1.3.4 ruff-0.3.7 safetensors-0.4.3 semantic-version-2.10.0 sentencepiece-0.2.0 shellingham-1.5.4 smart-open-6.4.0 sniffio-1.3.1 spacy-3.7.4 spacy-legacy-3.0.12 spacy-loggers-1.0.5 srsly-2.4.8 starlette-0.37.2 submitit-1.5.1 thinc-8.2.3 tokenizers-0.15.2 tomlkit-0.12.0 toolz-0.12.1 transformers-4.39.3 treetable-0.2.5 typer-0.9.4 uvicorn-0.29.0 wasabi-1.1.2 weasel-0.3.4 websockets-11.0.3 xformers-0.0.22.post7\n", + "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", + "\u001b[0mCloning into 'VoiceCraft'...\n", + "remote: Enumerating objects: 340, done.\u001b[K\n", + "remote: Counting objects: 100% (123/123), done.\u001b[K\n", + "remote: Compressing objects: 100% (57/57), done.\u001b[K\n", + "remote: Total 340 (delta 91), reused 76 (delta 66), pack-reused 217\u001b[K\n", + "Receiving objects: 100% (340/340), 2.47 MiB | 12.88 MiB/s, done.\n", + "Resolving deltas: 100% (198/198), done.\n" + ] + } + ] + }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "original:\n" - ] + "cell_type": "code", + "source": [ + "!mfa model download dictionary english_us_arpa && \\\n", + "mfa model download acoustic english_us_arpa\n" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "8pknHCCM5Umj", + "outputId": "149bfa85-96fe-4383-a5f0-a8e92c4dca26" + }, + "execution_count": 3, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[2;36m \u001b[0m\u001b[32mINFO \u001b[0m Saved model to \u001b[35m/root/Documents/MFA/pretrained_models/dictionary/\u001b[0m\u001b[95menglish_us_arpa.dict\u001b[0m, you \n", + "\u001b[2;36m \u001b[0m can now use english_us_arpa in place of dictionary paths in mfa commands. \n", + "\u001b[2;36m \u001b[0m\u001b[32mINFO \u001b[0m Saved model to \u001b[35m/root/Documents/MFA/pretrained_models/acoustic/\u001b[0m\u001b[95menglish_us_arpa.zip\u001b[0m, you can\n", + "\u001b[2;36m \u001b[0m now use english_us_arpa in place of acoustic paths in mfa commands. \n" + ] + } + ] }, { - "data": { - "text/html": [ - "\n", - " \n", - " " + "cell_type": "code", + "source": [ + "# simply installing audiocraft breaks due to no config, so move the default into site-packages\n", + "%cd /content/VoiceCraft\n", + "!git clone https://github.com/facebookresearch/audiocraft.git\n", + "!mv audiocraft/config /usr/local/lib/python3.10/site-packages/\n", + "!rm -rf audiocraft" ], - "text/plain": [ - "" + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Wdn4Hj9Z5ZbW", + "outputId": "4eb6db4b-e6de-4bd3-a8a3-586ada896145" + }, + "execution_count": 4, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "/content/VoiceCraft\n", + "Cloning into 'audiocraft'...\n", + "remote: Enumerating objects: 1426, done.\u001b[K\n", + "remote: Total 1426 (delta 0), reused 0 (delta 0), pack-reused 1426\u001b[K\n", + "Receiving objects: 100% (1426/1426), 1.95 MiB | 10.41 MiB/s, done.\n", + "Resolving deltas: 100% (802/802), done.\n" + ] + } ] - }, - "metadata": {}, - "output_type": "display_data" }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "edited:\n" - ] + "cell_type": "code", + "source": [ + "# import libs\n", + "import torch\n", + "import torchaudio\n", + "import os\n", + "import numpy as np\n", + "import random\n", + "os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\"\n", + "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"0\"\n", + "os.environ[\"USER\"] = \"YOUR_USERNAME\" # TODO change this to your username\n", + "\n", + "from data.tokenizer import (\n", + " AudioTokenizer,\n", + " TextTokenizer,\n", + ")\n", + "\n", + "from models import voicecraft" + ], + "metadata": { + "id": "SiWiiUpv5iQg" + }, + "execution_count": 5, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "# hyperparameters for inference\n", + "left_margin = 0.08\n", + "right_margin = 0.08\n", + "codec_audio_sr = 16000\n", + "codec_sr = 50\n", + "top_k = 0\n", + "top_p = 0.8\n", + "temperature = 1\n", + "kvcache = 0\n", + "# NOTE: adjust the below three arguments if the generation is not as good\n", + "seed = 1 # random seed magic\n", + "silence_tokens = [1388,1898,131]\n", + "stop_repetition = -1 # if there are long silence in the generated audio, reduce the stop_repetition to 3, 2 or even 1\n", + "# what this will do to the model is that the model will run sample_batch_size examples of the same audio, and pick the one that's the shortest\n", + "def seed_everything(seed):\n", + " os.environ['PYTHONHASHSEED'] = str(seed)\n", + " random.seed(seed)\n", + " np.random.seed(seed)\n", + " torch.manual_seed(seed)\n", + " torch.cuda.manual_seed(seed)\n", + " torch.backends.cudnn.benchmark = False\n", + " torch.backends.cudnn.deterministic = True\n", + "seed_everything(seed)\n", + "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", + "\n", + "# point to the original file or record the file\n", + "# write down the transcript for the file, or run whisper to get the transcript (and you can modify it if it's not accurate), save it as a .txt file\n", + "orig_audio = \"./demo/84_121550_000074_000000.wav\"\n", + "orig_transcript = \"But when I had approached so near to them The common object, which the sense deceives, Lost not by distance any of its marks,\"\n", + "# move the audio and transcript to temp folder\n", + "temp_folder = \"./demo/temp\"\n", + "os.makedirs(temp_folder, exist_ok=True)\n", + "os.system(f\"cp {orig_audio} {temp_folder}\")\n", + "filename = os.path.splitext(orig_audio.split(\"/\")[-1])[0]\n", + "with open(f\"{temp_folder}/{filename}.txt\", \"w\") as f:\n", + " f.write(orig_transcript)\n", + "# run MFA to get the alignment\n", + "align_temp = f\"{temp_folder}/mfa_alignments\"\n", + "os.makedirs(align_temp, exist_ok=True)\n", + "os.system(f\"mfa align -j 1 --clean --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp}\")\n", + "# if it fail, it could be because the audio is too hard for the alignment model, increasing the beam size usually solves the issue\n", + "# os.system(f\"mfa align -j 1 --clean --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp} --beam 1000 --retry_beam 2000\")\n", + "audio_fn = f\"{temp_folder}/{filename}.wav\"\n", + "transcript_fn = f\"{temp_folder}/{filename}.txt\"\n", + "align_fn = f\"{align_temp}/{filename}.csv\"" + ], + "metadata": { + "id": "a0pIv_pA5k0C" + }, + "execution_count": 6, + "outputs": [] }, { - "data": { - "text/html": [ - "\n", - " \n", - " " + "cell_type": "code", + "source": [ + "def get_mask_interval(ali_fn, word_span_ind, editType):\n", + " with open(ali_fn, \"r\") as rf:\n", + " data = [l.strip().split(\",\") for l in rf.readlines()]\n", + " data = data[1:]\n", + " tmp = word_span_ind.split(\",\")\n", + " s, e = int(tmp[0]), int(tmp[-1])\n", + " start = None\n", + " for j, item in enumerate(data):\n", + " if j == s and item[3] == \"words\":\n", + " if editType == 'insertion':\n", + " start = float(item[1])\n", + " else:\n", + " start = float(item[0])\n", + " if j == e and item[3] == \"words\":\n", + " if editType == 'insertion':\n", + " end = float(item[0])\n", + " else:\n", + " end = float(item[1])\n", + " assert start != None\n", + " break\n", + " return (start, end)\n" ], - "text/plain": [ - "" + "metadata": { + "id": "iIPNTtibF4OL" + }, + "execution_count": 9, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "# propose what do you want the target modified transcript to be\n", + "orig_transcript = \"But when I had approached so near to them which the sense deceives, Lost not by distance any of its marks,\"\n", + "target_transcript = \"But when I had approached so near which the sense deceives, Lost not by distance any of its marks,\" # deletes \"to them\"\n", + "\n", + "from edit_utils import parse_edit, get_edits\n", + "\n", + "# run the script to turn user input to the format that the model can take\n", + "operations, orig_span, new_span = parse_edit(orig_transcript, target_transcript)\n", + "\n", + "used_edits = get_edits(operations)\n", + "print(used_edits)\n", + "\n", + "def process_span(span):\n", + " if span[0] > span[1]:\n", + " raise RuntimeError(f\"example {audio_fn} failed\")\n", + " if span[0] == span[1]:\n", + " return [span[0]]\n", + " return span\n", + "\n", + "print(\"orig_span: \", orig_span)\n", + "print(\"new_span: \", new_span)\n", + "orig_span_save = [process_span(span) for span in orig_span]\n", + "new_span_save = [process_span(span) for span in new_span]\n", + "\n", + "orig_span_saves = [\",\".join([str(item) for item in span]) for span in orig_span_save]\n", + "new_span_saves = [\",\".join([str(item) for item in span]) for span in new_span_save]\n", + "\n", + "starting_intervals = []\n", + "ending_intervals = []\n", + "for i, orig_span_save in enumerate(orig_span_saves):\n", + " start, end = get_mask_interval(align_fn, orig_span_save, used_edits[i])\n", + " starting_intervals.append(start)\n", + " ending_intervals.append(end)\n", + "\n", + "print(\"intervals: \", starting_intervals, ending_intervals)\n", + "\n", + "info = torchaudio.info(audio_fn)\n", + "audio_dur = info.num_frames / info.sample_rate\n", + "morphed_span = [(max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur))\n", + " for start, end in zip(starting_intervals, ending_intervals)] # in seconds\n", + "\n", + "# span in codec frames\n", + "mask_interval = [[round(span[0]*codec_sr), round(span[1]*codec_sr)] for span in morphed_span]\n", + "mask_interval = torch.LongTensor(mask_interval) # [M,2], M==1 for now\n", + "\n", + "# load model, tokenizer, and other necessary files\n", + "voicecraft_name=\"giga330M.pth\" # or giga830M.pth, or the newer models at https://huggingface.co/pyp1/VoiceCraft/tree/main\n", + "ckpt_fn =f\"./pretrained_models/{voicecraft_name}\"\n", + "encodec_fn = \"./pretrained_models/encodec_4cb2048_giga.th\"\n", + "if not os.path.exists(ckpt_fn):\n", + " os.system(f\"wget https://huggingface.co/pyp1/VoiceCraft/resolve/main/{voicecraft_name}\\?download\\=true\")\n", + " os.system(f\"mv {voicecraft_name}\\?download\\=true ./pretrained_models/{voicecraft_name}\")\n", + "if not os.path.exists(encodec_fn):\n", + " os.system(f\"wget https://huggingface.co/pyp1/VoiceCraft/resolve/main/encodec_4cb2048_giga.th\")\n", + " os.system(f\"mv encodec_4cb2048_giga.th ./pretrained_models/encodec_4cb2048_giga.th\")\n", + "ckpt = torch.load(ckpt_fn, map_location=\"cpu\")\n", + "model = voicecraft.VoiceCraft(ckpt[\"config\"])\n", + "model.load_state_dict(ckpt[\"model\"])\n", + "model.to(device)\n", + "model.eval()\n", + "\n", + "phn2num = ckpt['phn2num']\n", + "\n", + "text_tokenizer = TextTokenizer(backend=\"espeak\")\n", + "audio_tokenizer = AudioTokenizer(signature=encodec_fn) # will also put the neural codec model on gpu\n", + "\n", + "# run the model to get the output\n", + "from inference_speech_editing_scale import inference_one_sample\n", + "\n", + "decode_config = {'top_k': top_k, 'top_p': top_p, 'temperature': temperature, 'stop_repetition': stop_repetition, 'kvcache': kvcache, \"codec_audio_sr\": codec_audio_sr, \"codec_sr\": codec_sr, \"silence_tokens\": silence_tokens}\n", + "orig_audio, new_audio = inference_one_sample(model, ckpt[\"config\"], phn2num, text_tokenizer, audio_tokenizer, audio_fn, target_transcript, mask_interval, device, decode_config)\n", + "\n", + "# save segments for comparison\n", + "orig_audio, new_audio = orig_audio[0].cpu(), new_audio[0].cpu()\n", + "# logging.info(f\"length of the resynthesize orig audio: {orig_audio.shape}\")\n", + "\n", + "# display the audio\n", + "from IPython.display import Audio\n", + "print(\"original:\")\n", + "display(Audio(orig_audio, rate=codec_audio_sr))\n", + "\n", + "print(\"edited:\")\n", + "display(Audio(new_audio, rate=codec_audio_sr))\n", + "\n", + "# # save the audio\n", + "# # output_dir\n", + "# output_dir = \"./demo/generated_se\"\n", + "# os.makedirs(output_dir, exist_ok=True)\n", + "\n", + "# save_fn_new = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_new_seed{seed}.wav\"\n", + "\n", + "# torchaudio.save(save_fn_new, new_audio, codec_audio_sr)\n", + "\n", + "# save_fn_orig = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_orig.wav\"\n", + "# if not os.path.isfile(save_fn_orig):\n", + "# orig_audio, orig_sr = torchaudio.load(audio_fn)\n", + "# if orig_sr != codec_audio_sr:\n", + "# orig_audio = torchaudio.transforms.Resample(orig_sr, codec_audio_sr)(orig_audio)\n", + "# torchaudio.save(save_fn_orig, orig_audio, codec_audio_sr)\n", + "\n", + "# # if you get error importing T5 in transformers\n", + "# # try\n", + "# # pip uninstall Pillow\n", + "# # pip install Pillow\n", + "# # you are likely to get warning looks like WARNING:phonemizer:words count mismatch on 300.0% of the lines (3/1), this can be safely ignored" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 280 + }, + "id": "krbq1mBM6GDE", + "outputId": "d9267aef-05b2-4276-ee8b-5687cab5c612" + }, + "execution_count": 13, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "['deletion']\n", + "orig_span: [[7, 8]]\n", + "new_span: [[6, 7]]\n", + "intervals: [1.91] [2.42]\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\n", + " warnings.warn(\"torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\")\n", + "WARNING:phonemizer:words count mismatch on 200.0% of the lines (2/1)\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "original:\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "\n", + " \n", + " " + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "edited:\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "\n", + " \n", + " " + ] + }, + "metadata": {} + } ] - }, - "metadata": {}, - "output_type": "display_data" } - ], - "source": [ - "editTypes_set = set(['substitution', 'insertion', 'deletion'])\n", - "# propose what do you want the target modified transcript to be\n", - "target_transcript = \"But when I saw the mirage of the lake in the distance, which the sense deceives, Lost not by distance any of its marks,\"\n", - "edit_type = \"substitution\"\n", - "assert edit_type in editTypes_set, f\"Invalid edit type {edit_type}. Must be one of {editTypes_set}.\"\n", - "\n", - "# if you want to do a second modification on top of the first one, write down the second modification (target_transcript2, type_of_modification2)\n", - "# make sure the two modification do not overlap, if they do, you need to combine them into one modification\n", - "\n", - "# run the script to turn user input to the format that the model can take\n", - "from edit_utils import get_span\n", - "orig_span, new_span = get_span(orig_transcript, target_transcript, edit_type)\n", - "if orig_span[0] > orig_span[1]:\n", - " RuntimeError(f\"example {audio_fn} failed\")\n", - "if orig_span[0] == orig_span[1]:\n", - " orig_span_save = [orig_span[0]]\n", - "else:\n", - " orig_span_save = orig_span\n", - "if new_span[0] == new_span[1]:\n", - " new_span_save = [new_span[0]]\n", - "else:\n", - " new_span_save = new_span\n", - "\n", - "orig_span_save = \",\".join([str(item) for item in orig_span_save])\n", - "new_span_save = \",\".join([str(item) for item in new_span_save])\n", - "from inference_speech_editing_scale import get_mask_interval\n", - "\n", - "start, end = get_mask_interval(align_fn, orig_span_save, edit_type)\n", - "info = torchaudio.info(audio_fn)\n", - "audio_dur = info.num_frames / info.sample_rate\n", - "morphed_span = (max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur)) # in seconds\n", - "\n", - "# span in codec frames\n", - "mask_interval = [[round(morphed_span[0]*codec_sr), round(morphed_span[1]*codec_sr)]]\n", - "mask_interval = torch.LongTensor(mask_interval) # [M,2], M==1 for now\n", - "\n", - "# load model, tokenizer, and other necessary files\n", - "voicecraft_name=\"giga330M.pth\" # or gigaHalfLibri330M_TTSEnhanced_max16s.pth, giga830M.pth\n", - "\n", - "# the new way of loading the model, with huggingface, recommended\n", - "from models import voicecraft\n", - "model = voicecraft.VoiceCraft.from_pretrained(f\"pyp1/VoiceCraft_{voicecraft_name.replace('.pth', '')}\")\n", - "phn2num = model.args.phn2num\n", - "config = vars(model.args)\n", - "model.to(device)\n", - "\n", - "# # the old way of loading the model\n", - "# from models import voicecraft\n", - "# filepath = hf_hub_download(repo_id=\"pyp1/VoiceCraft\", filename=voicecraft_name, repo_type=\"model\")\n", - "# ckpt = torch.load(filepath, map_location=\"cpu\")\n", - "# model = voicecraft.VoiceCraft(ckpt[\"config\"])\n", - "# model.load_state_dict(ckpt[\"model\"])\n", - "# config = vars(model.args)\n", - "# phn2num = ckpt[\"phn2num\"]\n", - "# model.to(device)\n", - "# model.eval()\n", - "\n", - "encodec_fn = \"./pretrained_models/encodec_4cb2048_giga.th\"\n", - "if not os.path.exists(encodec_fn):\n", - " os.system(f\"wget https://huggingface.co/pyp1/VoiceCraft/resolve/main/encodec_4cb2048_giga.th\")\n", - " os.system(f\"mv encodec_4cb2048_giga.th ./pretrained_models/encodec_4cb2048_giga.th\")\n", - "audio_tokenizer = AudioTokenizer(signature=encodec_fn) # will also put the neural codec model on gpu\n", - "\n", - "text_tokenizer = TextTokenizer(backend=\"espeak\")\n", - "\n", - "# run the model to get the output\n", - "from inference_speech_editing_scale import inference_one_sample\n", - "\n", - "decode_config = {'top_k': top_k, 'top_p': top_p, 'temperature': temperature, 'stop_repetition': stop_repetition, 'kvcache': kvcache, \"codec_audio_sr\": codec_audio_sr, \"codec_sr\": codec_sr, \"silence_tokens\": silence_tokens}\n", - "orig_audio, new_audio = inference_one_sample(model, ckpt[\"config\"], phn2num, text_tokenizer, audio_tokenizer, audio_fn, target_transcript, mask_interval, device, decode_config)\n", - " \n", - "# save segments for comparison\n", - "orig_audio, new_audio = orig_audio[0].cpu(), new_audio[0].cpu()\n", - "# logging.info(f\"length of the resynthesize orig audio: {orig_audio.shape}\")\n", - "\n", - "# display the audio\n", - "from IPython.display import Audio\n", - "print(\"original:\")\n", - "display(Audio(orig_audio, rate=codec_audio_sr))\n", - "\n", - "print(\"edited:\")\n", - "display(Audio(new_audio, rate=codec_audio_sr))\n", - "\n", - "# # save the audio\n", - "# # output_dir\n", - "# output_dir = \"./demo/generated_se\"\n", - "# os.makedirs(output_dir, exist_ok=True)\n", - "\n", - "# save_fn_new = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_new_seed{seed}.wav\"\n", - "\n", - "# torchaudio.save(save_fn_new, new_audio, codec_audio_sr)\n", - "\n", - "# save_fn_orig = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_orig.wav\"\n", - "# if not os.path.isfile(save_fn_orig):\n", - "# orig_audio, orig_sr = torchaudio.load(audio_fn)\n", - "# if orig_sr != codec_audio_sr:\n", - "# orig_audio = torchaudio.transforms.Resample(orig_sr, codec_audio_sr)(orig_audio)\n", - "# torchaudio.save(save_fn_orig, orig_audio, codec_audio_sr)\n", - "\n", - "# # if you get error importing T5 in transformers\n", - "# # try \n", - "# # pip uninstall Pillow\n", - "# # pip install Pillow\n", - "# # you are likely to get warning looks like WARNING:phonemizer:words count mismatch on 300.0% of the lines (3/1), this can be safely ignored" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "voicecraft", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.9.18" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} + ] +} \ No newline at end of file From 2168efc49d88d4cc41d9ec4714f9accde8991874 Mon Sep 17 00:00:00 2001 From: Pranay Gosar Date: Wed, 17 Apr 2024 12:35:07 -0500 Subject: [PATCH 2/8] remove cell outputs --- inference_speech_editing.ipynb | 4115 +------------------------------- 1 file changed, 44 insertions(+), 4071 deletions(-) diff --git a/inference_speech_editing.ipynb b/inference_speech_editing.ipynb index 2edef05..588d91a 100644 --- a/inference_speech_editing.ipynb +++ b/inference_speech_editing.ipynb @@ -1,3982 +1,12 @@ { - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "provenance": [], - "gpuType": "T4" - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "language_info": { - "name": "python" - }, - "accelerator": "GPU" - }, "cells": [ - { - "cell_type": "markdown", - "source": [ - "### This will crash the kernel the first time. This is expected - if you rerun from the start, it will work." - ], - "metadata": { - "id": "2qVBkPyM4-Fc" - } - }, { "cell_type": "code", - "source": [ - "!apt-get install -y git-core ffmpeg espeak-ng\n", - "!pip install -q condacolab\n", - "import condacolab\n", - "condacolab.install()\n", - "condacolab.check()" - ], - "metadata": { - "id": "OHGB5aX75EZ7", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "d102e3c9-e2c5-40e0-bde0-3c1a78ca82cc" - }, - "execution_count": 1, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Reading package lists... Done\n", - "Building dependency tree... Done\n", - "Reading state information... Done\n", - "Note, selecting 'git' instead of 'git-core'\n", - "espeak-ng is already the newest version (1.50+dfsg-10).\n", - "git is already the newest version (1:2.34.1-1ubuntu1.10).\n", - "ffmpeg is already the newest version (7:4.4.2-0ubuntu0.22.04.1).\n", - "0 upgraded, 0 newly installed, 0 to remove and 45 not upgraded.\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0m✨🍰✨ Everything looks OK!\n", - "✨🍰✨ Everything looks OK!\n" - ] - } - ] - }, - { - "cell_type": "code", - "source": [ - "!echo -e \"Grab a cup a coffee and a slice of pizza...\\n\\n\"\n", - "!conda install -y -c conda-forge montreal-forced-aligner=2.2.17 openfst=1.8.2 kaldi=5.5.1068 && \\\n", - " pip install torch==2.1.0 && \\\n", - " pip install tensorboard==2.16.2 && \\\n", - " pip install phonemizer==3.2.1 && \\\n", - " pip install torchaudio==2.1.0 && \\\n", - " pip install datasets==2.16.0 && \\\n", - " pip install torchmetrics==0.11.1 && \\\n", - " pip install torchvision==0.16.0\n", - "\n", - "!pip install -U git+https://git@github.com/facebookresearch/audiocraft#egg=audiocraft\n", - "!git clone https://github.com/jasonppy/VoiceCraft.git" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "Z57Oocvy5ILk", - "outputId": "1e75f151-05da-4763-a07b-45ff445edb94" - }, - "execution_count": 2, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Grab a cup a coffee and a slice of pizza...\n", - "\n", - "\n", - "Channels:\n", - " - conda-forge\n", - "Platform: linux-64\n", - "Collecting package metadata (repodata.json): - \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\bdone\n", - "Solving environment: \\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\bdone\n", - "\n", - "\n", - "==> WARNING: A newer version of conda exists. <==\n", - " current version: 23.11.0\n", - " latest version: 24.3.0\n", - "\n", - "Please update conda by running\n", - "\n", - " $ conda update -n base -c conda-forge conda\n", - "\n", - "\n", - "\n", - "## Package Plan ##\n", - "\n", - " environment location: /usr/local\n", - "\n", - " added / updated specs:\n", - " - kaldi=5.5.1068\n", - " - montreal-forced-aligner=2.2.17\n", - " - openfst=1.8.2\n", - "\n", - "\n", - "The following packages will be downloaded:\n", - "\n", - " package | build\n", - " ---------------------------|-----------------\n", - " aom-3.7.1 | h59595ed_0 2.6 MB conda-forge\n", - " atk-1.0-2.38.0 | hd4edc92_1 539 KB conda-forge\n", - " audioread-3.0.1 | py310hff52083_1 36 KB conda-forge\n", - " baumwelch-0.3.7 | h00ab1b0_5 376 KB conda-forge\n", - " biopython-1.79 | py310h5764c6d_3 2.7 MB conda-forge\n", - " brotli-1.1.0 | hd590300_1 19 KB conda-forge\n", - " brotli-bin-1.1.0 | hd590300_1 19 KB conda-forge\n", - " ca-certificates-2024.2.2 | hbcca054_0 152 KB conda-forge\n", - " cairo-1.18.0 | h3faef2a_0 959 KB conda-forge\n", - " certifi-2024.2.2 | pyhd8ed1ab_0 157 KB conda-forge\n", - " click-8.1.7 |unix_pyh707e725_0 82 KB conda-forge\n", - " contourpy-1.2.1 | py310hd41b1e2_0 236 KB conda-forge\n", - " cudatoolkit-11.8.0 | h4ba93d1_13 682.5 MB conda-forge\n", - " cycler-0.12.1 | pyhd8ed1ab_0 13 KB conda-forge\n", - " cython-3.0.10 | py310hc6cd4ac_0 3.1 MB conda-forge\n", - " dataclassy-1.0.1 | pyhd8ed1ab_0 31 KB conda-forge\n", - " dav1d-1.2.1 | hd590300_0 742 KB conda-forge\n", - " decorator-5.1.1 | pyhd8ed1ab_0 12 KB conda-forge\n", - " expat-2.6.2 | h59595ed_0 134 KB conda-forge\n", - " ffmpeg-6.1.1 | gpl_h186bccc_100 9.3 MB conda-forge\n", - " font-ttf-dejavu-sans-mono-2.37| hab24e00_0 388 KB conda-forge\n", - " font-ttf-inconsolata-3.000 | h77eed37_0 94 KB conda-forge\n", - " font-ttf-source-code-pro-2.038| h77eed37_0 684 KB conda-forge\n", - " font-ttf-ubuntu-0.83 | h77eed37_1 1.5 MB conda-forge\n", - " fontconfig-2.14.2 | h14ed4e7_0 266 KB conda-forge\n", - " fonts-conda-ecosystem-1 | 0 4 KB conda-forge\n", - " fonts-conda-forge-1 | 0 4 KB conda-forge\n", - " fonttools-4.51.0 | py310h2372a71_0 2.2 MB conda-forge\n", - " freetype-2.12.1 | h267a509_2 620 KB conda-forge\n", - " fribidi-1.0.10 | h36c2ea0_0 112 KB conda-forge\n", - " gdk-pixbuf-2.42.10 | h829c605_6 563 KB conda-forge\n", - " gettext-0.22.5 | h59595ed_2 464 KB conda-forge\n", - " gettext-tools-0.22.5 | h59595ed_2 2.6 MB conda-forge\n", - " giflib-5.2.2 | hd590300_0 75 KB conda-forge\n", - " gmp-6.3.0 | h59595ed_1 556 KB conda-forge\n", - " gnutls-3.7.9 | hb077bed_0 1.9 MB conda-forge\n", - " graphite2-1.3.13 | h59595ed_1003 95 KB conda-forge\n", - " graphviz-9.0.0 | h78e8752_1 2.2 MB conda-forge\n", - " greenlet-3.0.3 | py310hc6cd4ac_0 206 KB conda-forge\n", - " gtk2-2.24.33 | h280cfa0_4 6.2 MB conda-forge\n", - " gts-0.7.6 | h977cf35_4 311 KB conda-forge\n", - " harfbuzz-8.3.0 | h3d44ed6_0 1.5 MB conda-forge\n", - " hdbscan-0.8.33 | py310h1f7b6fc_4 505 KB conda-forge\n", - " importlib-metadata-7.1.0 | pyha770c72_0 26 KB conda-forge\n", - " joblib-1.4.0 | pyhd8ed1ab_0 215 KB conda-forge\n", - " kaldi-5.5.1068 |cuda112h971fcfb_2 22.6 MB conda-forge\n", - " kiwisolver-1.4.5 | py310hd41b1e2_1 71 KB conda-forge\n", - " kneed-0.8.5 | pyhd8ed1ab_0 15 KB conda-forge\n", - " lame-3.100 | h166bdaf_1003 496 KB conda-forge\n", - " lazy_loader-0.4 | pyhd8ed1ab_0 16 KB conda-forge\n", - " lcms2-2.16 | hb7c19ff_0 239 KB conda-forge\n", - " lerc-4.0.0 | h27087fc_0 275 KB conda-forge\n", - " libasprintf-0.22.5 | h661eb56_2 42 KB conda-forge\n", - " libasprintf-devel-0.22.5 | h661eb56_2 33 KB conda-forge\n", - " libass-0.17.1 | h8fe9dca_1 124 KB conda-forge\n", - " libblas-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", - " libbrotlicommon-1.1.0 | hd590300_1 68 KB conda-forge\n", - " libbrotlidec-1.1.0 | hd590300_1 32 KB conda-forge\n", - " libbrotlienc-1.1.0 | hd590300_1 276 KB conda-forge\n", - " libcblas-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", - " libdeflate-1.20 | hd590300_0 70 KB conda-forge\n", - " libdrm-2.4.120 | hd590300_0 296 KB conda-forge\n", - " libexpat-2.6.2 | h59595ed_0 72 KB conda-forge\n", - " libflac-1.4.3 | h59595ed_0 385 KB conda-forge\n", - " libgd-2.3.3 | h119a65a_9 219 KB conda-forge\n", - " libgettextpo-0.22.5 | h59595ed_2 167 KB conda-forge\n", - " libgettextpo-devel-0.22.5 | h59595ed_2 36 KB conda-forge\n", - " libgfortran-ng-13.2.0 | h69a702a_5 23 KB conda-forge\n", - " libgfortran5-13.2.0 | ha4646dd_5 1.4 MB conda-forge\n", - " libglib-2.80.0 | hf2295e7_5 3.7 MB conda-forge\n", - " libidn2-2.3.7 | hd590300_0 124 KB conda-forge\n", - " libjpeg-turbo-3.0.0 | hd590300_1 604 KB conda-forge\n", - " liblapack-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", - " liblapacke-3.9.0 |22_linux64_openblas 14 KB conda-forge\n", - " libllvm14-14.0.6 | hcd5def8_4 30.0 MB conda-forge\n", - " libmagma-2.7.1 | hc72dce7_6 201.2 MB conda-forge\n", - " libmagma_sparse-2.7.1 | h8354cda_6 7.1 MB conda-forge\n", - " libogg-1.3.4 | h7f98852_1 206 KB conda-forge\n", - " libopenblas-0.3.27 |pthreads_h413a1c8_0 5.3 MB conda-forge\n", - " libopus-1.3.1 | h7f98852_1 255 KB conda-forge\n", - " libpciaccess-0.18 | hd590300_0 28 KB conda-forge\n", - " libpng-1.6.43 | h2797004_0 281 KB conda-forge\n", - " libpq-16.1 | h33b98f1_7 2.4 MB conda-forge\n", - " librosa-0.10.1 | pyhd8ed1ab_0 189 KB conda-forge\n", - " librsvg-2.56.3 | he3f83f7_1 5.6 MB conda-forge\n", - " libsndfile-1.2.2 | hc60ed4a_1 346 KB conda-forge\n", - " libtasn1-4.19.0 | h166bdaf_0 114 KB conda-forge\n", - " libtiff-4.6.0 | h1dd3fc0_3 276 KB conda-forge\n", - " libunistring-0.9.10 | h7f98852_0 1.4 MB conda-forge\n", - " libva-2.21.0 | hd590300_0 185 KB conda-forge\n", - " libvorbis-1.3.7 | h9c3ff4c_0 280 KB conda-forge\n", - " libvpx-1.13.1 | h59595ed_0 982 KB conda-forge\n", - " libwebp-1.3.2 | h658648e_1 83 KB conda-forge\n", - " libwebp-base-1.3.2 | hd590300_1 424 KB conda-forge\n", - " libxcb-1.15 | h0b41bf4_0 375 KB conda-forge\n", - " llvmlite-0.42.0 | py310h1b8f574_1 3.2 MB conda-forge\n", - " mad-0.15.1b | h9c3ff4c_1 113 KB conda-forge\n", - " magma-2.7.1 | ha770c72_6 100 KB conda-forge\n", - " markdown-it-py-3.0.0 | pyhd8ed1ab_0 63 KB conda-forge\n", - " matplotlib-base-3.8.4 | py310h62c0568_0 6.7 MB conda-forge\n", - " mdurl-0.1.2 | pyhd8ed1ab_0 14 KB conda-forge\n", - " montreal-forced-aligner-2.2.17| pyhd8ed1ab_0 225 KB conda-forge\n", - " mpg123-1.32.6 | h59595ed_0 480 KB conda-forge\n", - " msgpack-python-1.0.7 | py310hd41b1e2_0 192 KB conda-forge\n", - " munkres-1.1.4 | pyh9f0ad1d_0 12 KB conda-forge\n", - " nettle-3.9.1 | h7ab15ed_0 988 KB conda-forge\n", - " ngram-1.3.14 | h924138e_2 3.4 MB conda-forge\n", - " numba-0.59.1 | py310h7dc5dd1_0 4.1 MB conda-forge\n", - " numpy-1.26.4 | py310hb13e2d6_0 6.7 MB conda-forge\n", - " openfst-1.8.2 | h924138e_2 7.4 MB conda-forge\n", - " openh264-2.4.0 | h59595ed_0 719 KB conda-forge\n", - " openjpeg-2.5.2 | h488ebb8_0 334 KB conda-forge\n", - " openssl-3.2.1 | hd590300_1 2.7 MB conda-forge\n", - " p11-kit-0.24.1 | hc5aa10d_0 4.5 MB conda-forge\n", - " pandas-2.2.2 | py310hcc13569_0 12.4 MB conda-forge\n", - " pango-1.52.2 | ha41ecd1_0 436 KB conda-forge\n", - " patsy-0.5.6 | pyhd8ed1ab_0 183 KB conda-forge\n", - " pcre2-10.43 | hcad00b1_0 929 KB conda-forge\n", - " pgvector-0.6.0 | h634da08_0 66 KB conda-forge\n", - " pgvector-python-0.2.5 | pyhe093146_0 14 KB conda-forge\n", - " pillow-10.3.0 | py310hf73ecf8_0 39.8 MB conda-forge\n", - " pixman-0.43.2 | h59595ed_0 378 KB conda-forge\n", - " pooch-1.8.1 | pyhd8ed1ab_0 51 KB conda-forge\n", - " postgresql-16.1 | h7387d8b_7 5.1 MB conda-forge\n", - " praatio-6.0.0 | pyhd8ed1ab_0 60 KB conda-forge\n", - " psycopg2-2.9.9 | py310h275853b_0 169 KB conda-forge\n", - " pthread-stubs-0.4 | h36c2ea0_1001 5 KB conda-forge\n", - " pygments-2.17.2 | pyhd8ed1ab_0 840 KB conda-forge\n", - " pynini-2.1.5 | py310hd41b1e2_6 1.5 MB conda-forge\n", - " pyparsing-3.1.2 | pyhd8ed1ab_0 87 KB conda-forge\n", - " pysoundfile-0.12.1 | pyhd8ed1ab_0 27 KB conda-forge\n", - " python-dateutil-2.9.0 | pyhd8ed1ab_0 218 KB conda-forge\n", - " python-tzdata-2024.1 | pyhd8ed1ab_0 141 KB conda-forge\n", - " pytz-2024.1 | pyhd8ed1ab_0 184 KB conda-forge\n", - " pyyaml-6.0.1 | py310h2372a71_1 167 KB conda-forge\n", - " rich-13.7.1 | pyhd8ed1ab_0 180 KB conda-forge\n", - " rich-click-1.7.4 | pyhd8ed1ab_0 32 KB conda-forge\n", - " scikit-learn-1.2.2 | py310hf7d194e_2 7.3 MB conda-forge\n", - " scipy-1.13.0 | py310hb13e2d6_0 15.6 MB conda-forge\n", - " seaborn-0.13.2 | hd8ed1ab_0 7 KB conda-forge\n", - " seaborn-base-0.13.2 | pyhd8ed1ab_0 229 KB conda-forge\n", - " six-1.16.0 | pyh6c4a22f_0 14 KB conda-forge\n", - " sox-14.4.2 | ha5cc309_1018 499 KB conda-forge\n", - " soxr-0.1.3 | h0b41bf4_3 128 KB conda-forge\n", - " soxr-python-0.3.7 | py310h1f7b6fc_0 265 KB conda-forge\n", - " sqlalchemy-2.0.29 | py310h2372a71_0 2.7 MB conda-forge\n", - " sqlite-3.44.2 | h2c6b66d_0 817 KB conda-forge\n", - " statsmodels-0.14.1 | py310h1f7b6fc_0 10.5 MB conda-forge\n", - " svt-av1-1.8.0 | h59595ed_0 2.5 MB conda-forge\n", - " threadpoolctl-3.4.0 | pyhc1e730c_0 22 KB conda-forge\n", - " typing-extensions-4.11.0 | hd8ed1ab_0 10 KB conda-forge\n", - " typing_extensions-4.11.0 | pyha770c72_0 37 KB conda-forge\n", - " tzcode-2024a | h3f72095_0 68 KB conda-forge\n", - " unicodedata2-15.1.0 | py310h2372a71_0 365 KB conda-forge\n", - " x264-1!164.3095 | h166bdaf_2 877 KB conda-forge\n", - " x265-3.5 | h924138e_3 3.2 MB conda-forge\n", - " xorg-fixesproto-5.0 | h7f98852_1002 9 KB conda-forge\n", - " xorg-kbproto-1.0.7 | h7f98852_1002 27 KB conda-forge\n", - " xorg-libice-1.1.1 | hd590300_0 57 KB conda-forge\n", - " xorg-libsm-1.2.4 | h7391055_0 27 KB conda-forge\n", - " xorg-libx11-1.8.9 | h8ee46fc_0 809 KB conda-forge\n", - " xorg-libxau-1.0.11 | hd590300_0 14 KB conda-forge\n", - " xorg-libxdmcp-1.1.3 | h7f98852_0 19 KB conda-forge\n", - " xorg-libxext-1.3.4 | h0b41bf4_2 49 KB conda-forge\n", - " xorg-libxfixes-5.0.3 | h7f98852_1004 18 KB conda-forge\n", - " xorg-libxrender-0.9.11 | hd590300_0 37 KB conda-forge\n", - " xorg-renderproto-0.11.1 | h7f98852_1002 9 KB conda-forge\n", - " xorg-xextproto-7.3.0 | h0b41bf4_1003 30 KB conda-forge\n", - " xorg-xproto-7.0.31 | h7f98852_1007 73 KB conda-forge\n", - " yaml-0.2.5 | h7f98852_2 87 KB conda-forge\n", - " zipp-3.17.0 | pyhd8ed1ab_0 19 KB conda-forge\n", - " zlib-1.2.13 | hd590300_5 91 KB conda-forge\n", - " ------------------------------------------------------------\n", - " Total: 1.14 GB\n", - "\n", - "The following NEW packages will be INSTALLED:\n", - "\n", - " aom conda-forge/linux-64::aom-3.7.1-h59595ed_0 \n", - " atk-1.0 conda-forge/linux-64::atk-1.0-2.38.0-hd4edc92_1 \n", - " audioread conda-forge/linux-64::audioread-3.0.1-py310hff52083_1 \n", - " baumwelch conda-forge/linux-64::baumwelch-0.3.7-h00ab1b0_5 \n", - " biopython conda-forge/linux-64::biopython-1.79-py310h5764c6d_3 \n", - " brotli conda-forge/linux-64::brotli-1.1.0-hd590300_1 \n", - " brotli-bin conda-forge/linux-64::brotli-bin-1.1.0-hd590300_1 \n", - " cairo conda-forge/linux-64::cairo-1.18.0-h3faef2a_0 \n", - " click conda-forge/noarch::click-8.1.7-unix_pyh707e725_0 \n", - " contourpy conda-forge/linux-64::contourpy-1.2.1-py310hd41b1e2_0 \n", - " cudatoolkit conda-forge/linux-64::cudatoolkit-11.8.0-h4ba93d1_13 \n", - " cycler conda-forge/noarch::cycler-0.12.1-pyhd8ed1ab_0 \n", - " cython conda-forge/linux-64::cython-3.0.10-py310hc6cd4ac_0 \n", - " dataclassy conda-forge/noarch::dataclassy-1.0.1-pyhd8ed1ab_0 \n", - " dav1d conda-forge/linux-64::dav1d-1.2.1-hd590300_0 \n", - " decorator conda-forge/noarch::decorator-5.1.1-pyhd8ed1ab_0 \n", - " expat conda-forge/linux-64::expat-2.6.2-h59595ed_0 \n", - " ffmpeg conda-forge/linux-64::ffmpeg-6.1.1-gpl_h186bccc_100 \n", - " font-ttf-dejavu-s~ conda-forge/noarch::font-ttf-dejavu-sans-mono-2.37-hab24e00_0 \n", - " font-ttf-inconsol~ conda-forge/noarch::font-ttf-inconsolata-3.000-h77eed37_0 \n", - " font-ttf-source-c~ conda-forge/noarch::font-ttf-source-code-pro-2.038-h77eed37_0 \n", - " font-ttf-ubuntu conda-forge/noarch::font-ttf-ubuntu-0.83-h77eed37_1 \n", - " fontconfig conda-forge/linux-64::fontconfig-2.14.2-h14ed4e7_0 \n", - " fonts-conda-ecosy~ conda-forge/noarch::fonts-conda-ecosystem-1-0 \n", - " fonts-conda-forge conda-forge/noarch::fonts-conda-forge-1-0 \n", - " fonttools conda-forge/linux-64::fonttools-4.51.0-py310h2372a71_0 \n", - " freetype conda-forge/linux-64::freetype-2.12.1-h267a509_2 \n", - " fribidi conda-forge/linux-64::fribidi-1.0.10-h36c2ea0_0 \n", - " gdk-pixbuf conda-forge/linux-64::gdk-pixbuf-2.42.10-h829c605_6 \n", - " gettext conda-forge/linux-64::gettext-0.22.5-h59595ed_2 \n", - " gettext-tools conda-forge/linux-64::gettext-tools-0.22.5-h59595ed_2 \n", - " giflib conda-forge/linux-64::giflib-5.2.2-hd590300_0 \n", - " gmp conda-forge/linux-64::gmp-6.3.0-h59595ed_1 \n", - " gnutls conda-forge/linux-64::gnutls-3.7.9-hb077bed_0 \n", - " graphite2 conda-forge/linux-64::graphite2-1.3.13-h59595ed_1003 \n", - " graphviz conda-forge/linux-64::graphviz-9.0.0-h78e8752_1 \n", - " greenlet conda-forge/linux-64::greenlet-3.0.3-py310hc6cd4ac_0 \n", - " gtk2 conda-forge/linux-64::gtk2-2.24.33-h280cfa0_4 \n", - " gts conda-forge/linux-64::gts-0.7.6-h977cf35_4 \n", - " harfbuzz conda-forge/linux-64::harfbuzz-8.3.0-h3d44ed6_0 \n", - " hdbscan conda-forge/linux-64::hdbscan-0.8.33-py310h1f7b6fc_4 \n", - " importlib-metadata conda-forge/noarch::importlib-metadata-7.1.0-pyha770c72_0 \n", - " joblib conda-forge/noarch::joblib-1.4.0-pyhd8ed1ab_0 \n", - " kaldi conda-forge/linux-64::kaldi-5.5.1068-cuda112h971fcfb_2 \n", - " kiwisolver conda-forge/linux-64::kiwisolver-1.4.5-py310hd41b1e2_1 \n", - " kneed conda-forge/noarch::kneed-0.8.5-pyhd8ed1ab_0 \n", - " lame conda-forge/linux-64::lame-3.100-h166bdaf_1003 \n", - " lazy_loader conda-forge/noarch::lazy_loader-0.4-pyhd8ed1ab_0 \n", - " lcms2 conda-forge/linux-64::lcms2-2.16-hb7c19ff_0 \n", - " lerc conda-forge/linux-64::lerc-4.0.0-h27087fc_0 \n", - " libasprintf conda-forge/linux-64::libasprintf-0.22.5-h661eb56_2 \n", - " libasprintf-devel conda-forge/linux-64::libasprintf-devel-0.22.5-h661eb56_2 \n", - " libass conda-forge/linux-64::libass-0.17.1-h8fe9dca_1 \n", - " libblas conda-forge/linux-64::libblas-3.9.0-22_linux64_openblas \n", - " libbrotlicommon conda-forge/linux-64::libbrotlicommon-1.1.0-hd590300_1 \n", - " libbrotlidec conda-forge/linux-64::libbrotlidec-1.1.0-hd590300_1 \n", - " libbrotlienc conda-forge/linux-64::libbrotlienc-1.1.0-hd590300_1 \n", - " libcblas conda-forge/linux-64::libcblas-3.9.0-22_linux64_openblas \n", - " libdeflate conda-forge/linux-64::libdeflate-1.20-hd590300_0 \n", - " libdrm conda-forge/linux-64::libdrm-2.4.120-hd590300_0 \n", - " libexpat conda-forge/linux-64::libexpat-2.6.2-h59595ed_0 \n", - " libflac conda-forge/linux-64::libflac-1.4.3-h59595ed_0 \n", - " libgd conda-forge/linux-64::libgd-2.3.3-h119a65a_9 \n", - " libgettextpo conda-forge/linux-64::libgettextpo-0.22.5-h59595ed_2 \n", - " libgettextpo-devel conda-forge/linux-64::libgettextpo-devel-0.22.5-h59595ed_2 \n", - " libgfortran-ng conda-forge/linux-64::libgfortran-ng-13.2.0-h69a702a_5 \n", - " libgfortran5 conda-forge/linux-64::libgfortran5-13.2.0-ha4646dd_5 \n", - " libglib conda-forge/linux-64::libglib-2.80.0-hf2295e7_5 \n", - " libidn2 conda-forge/linux-64::libidn2-2.3.7-hd590300_0 \n", - " libjpeg-turbo conda-forge/linux-64::libjpeg-turbo-3.0.0-hd590300_1 \n", - " liblapack conda-forge/linux-64::liblapack-3.9.0-22_linux64_openblas \n", - " liblapacke conda-forge/linux-64::liblapacke-3.9.0-22_linux64_openblas \n", - " libllvm14 conda-forge/linux-64::libllvm14-14.0.6-hcd5def8_4 \n", - " libmagma conda-forge/linux-64::libmagma-2.7.1-hc72dce7_6 \n", - " libmagma_sparse conda-forge/linux-64::libmagma_sparse-2.7.1-h8354cda_6 \n", - " libogg conda-forge/linux-64::libogg-1.3.4-h7f98852_1 \n", - " libopenblas conda-forge/linux-64::libopenblas-0.3.27-pthreads_h413a1c8_0 \n", - " libopus conda-forge/linux-64::libopus-1.3.1-h7f98852_1 \n", - " libpciaccess conda-forge/linux-64::libpciaccess-0.18-hd590300_0 \n", - " libpng conda-forge/linux-64::libpng-1.6.43-h2797004_0 \n", - " libpq conda-forge/linux-64::libpq-16.1-h33b98f1_7 \n", - " librosa conda-forge/noarch::librosa-0.10.1-pyhd8ed1ab_0 \n", - " librsvg conda-forge/linux-64::librsvg-2.56.3-he3f83f7_1 \n", - " libsndfile conda-forge/linux-64::libsndfile-1.2.2-hc60ed4a_1 \n", - " libtasn1 conda-forge/linux-64::libtasn1-4.19.0-h166bdaf_0 \n", - " libtiff conda-forge/linux-64::libtiff-4.6.0-h1dd3fc0_3 \n", - " libunistring conda-forge/linux-64::libunistring-0.9.10-h7f98852_0 \n", - " libva conda-forge/linux-64::libva-2.21.0-hd590300_0 \n", - " libvorbis conda-forge/linux-64::libvorbis-1.3.7-h9c3ff4c_0 \n", - " libvpx conda-forge/linux-64::libvpx-1.13.1-h59595ed_0 \n", - " libwebp conda-forge/linux-64::libwebp-1.3.2-h658648e_1 \n", - " libwebp-base conda-forge/linux-64::libwebp-base-1.3.2-hd590300_1 \n", - " libxcb conda-forge/linux-64::libxcb-1.15-h0b41bf4_0 \n", - " llvmlite conda-forge/linux-64::llvmlite-0.42.0-py310h1b8f574_1 \n", - " mad conda-forge/linux-64::mad-0.15.1b-h9c3ff4c_1 \n", - " magma conda-forge/linux-64::magma-2.7.1-ha770c72_6 \n", - " markdown-it-py conda-forge/noarch::markdown-it-py-3.0.0-pyhd8ed1ab_0 \n", - " matplotlib-base conda-forge/linux-64::matplotlib-base-3.8.4-py310h62c0568_0 \n", - " mdurl conda-forge/noarch::mdurl-0.1.2-pyhd8ed1ab_0 \n", - " montreal-forced-a~ conda-forge/noarch::montreal-forced-aligner-2.2.17-pyhd8ed1ab_0 \n", - " mpg123 conda-forge/linux-64::mpg123-1.32.6-h59595ed_0 \n", - " msgpack-python conda-forge/linux-64::msgpack-python-1.0.7-py310hd41b1e2_0 \n", - " munkres conda-forge/noarch::munkres-1.1.4-pyh9f0ad1d_0 \n", - " nettle conda-forge/linux-64::nettle-3.9.1-h7ab15ed_0 \n", - " ngram conda-forge/linux-64::ngram-1.3.14-h924138e_2 \n", - " numba conda-forge/linux-64::numba-0.59.1-py310h7dc5dd1_0 \n", - " numpy conda-forge/linux-64::numpy-1.26.4-py310hb13e2d6_0 \n", - " openfst conda-forge/linux-64::openfst-1.8.2-h924138e_2 \n", - " openh264 conda-forge/linux-64::openh264-2.4.0-h59595ed_0 \n", - " openjpeg conda-forge/linux-64::openjpeg-2.5.2-h488ebb8_0 \n", - " p11-kit conda-forge/linux-64::p11-kit-0.24.1-hc5aa10d_0 \n", - " pandas conda-forge/linux-64::pandas-2.2.2-py310hcc13569_0 \n", - " pango conda-forge/linux-64::pango-1.52.2-ha41ecd1_0 \n", - " patsy conda-forge/noarch::patsy-0.5.6-pyhd8ed1ab_0 \n", - " pcre2 conda-forge/linux-64::pcre2-10.43-hcad00b1_0 \n", - " pgvector conda-forge/linux-64::pgvector-0.6.0-h634da08_0 \n", - " pgvector-python conda-forge/noarch::pgvector-python-0.2.5-pyhe093146_0 \n", - " pillow conda-forge/linux-64::pillow-10.3.0-py310hf73ecf8_0 \n", - " pixman conda-forge/linux-64::pixman-0.43.2-h59595ed_0 \n", - " pooch conda-forge/noarch::pooch-1.8.1-pyhd8ed1ab_0 \n", - " postgresql conda-forge/linux-64::postgresql-16.1-h7387d8b_7 \n", - " praatio conda-forge/noarch::praatio-6.0.0-pyhd8ed1ab_0 \n", - " psycopg2 conda-forge/linux-64::psycopg2-2.9.9-py310h275853b_0 \n", - " pthread-stubs conda-forge/linux-64::pthread-stubs-0.4-h36c2ea0_1001 \n", - " pygments conda-forge/noarch::pygments-2.17.2-pyhd8ed1ab_0 \n", - " pynini conda-forge/linux-64::pynini-2.1.5-py310hd41b1e2_6 \n", - " pyparsing conda-forge/noarch::pyparsing-3.1.2-pyhd8ed1ab_0 \n", - " pysoundfile conda-forge/noarch::pysoundfile-0.12.1-pyhd8ed1ab_0 \n", - " python-dateutil conda-forge/noarch::python-dateutil-2.9.0-pyhd8ed1ab_0 \n", - " python-tzdata conda-forge/noarch::python-tzdata-2024.1-pyhd8ed1ab_0 \n", - " pytz conda-forge/noarch::pytz-2024.1-pyhd8ed1ab_0 \n", - " pyyaml conda-forge/linux-64::pyyaml-6.0.1-py310h2372a71_1 \n", - " rich conda-forge/noarch::rich-13.7.1-pyhd8ed1ab_0 \n", - " rich-click conda-forge/noarch::rich-click-1.7.4-pyhd8ed1ab_0 \n", - " scikit-learn conda-forge/linux-64::scikit-learn-1.2.2-py310hf7d194e_2 \n", - " scipy conda-forge/linux-64::scipy-1.13.0-py310hb13e2d6_0 \n", - " seaborn conda-forge/noarch::seaborn-0.13.2-hd8ed1ab_0 \n", - " seaborn-base conda-forge/noarch::seaborn-base-0.13.2-pyhd8ed1ab_0 \n", - " six conda-forge/noarch::six-1.16.0-pyh6c4a22f_0 \n", - " sox conda-forge/linux-64::sox-14.4.2-ha5cc309_1018 \n", - " soxr conda-forge/linux-64::soxr-0.1.3-h0b41bf4_3 \n", - " soxr-python conda-forge/linux-64::soxr-python-0.3.7-py310h1f7b6fc_0 \n", - " sqlalchemy conda-forge/linux-64::sqlalchemy-2.0.29-py310h2372a71_0 \n", - " sqlite conda-forge/linux-64::sqlite-3.44.2-h2c6b66d_0 \n", - " statsmodels conda-forge/linux-64::statsmodels-0.14.1-py310h1f7b6fc_0 \n", - " svt-av1 conda-forge/linux-64::svt-av1-1.8.0-h59595ed_0 \n", - " threadpoolctl conda-forge/noarch::threadpoolctl-3.4.0-pyhc1e730c_0 \n", - " typing-extensions conda-forge/noarch::typing-extensions-4.11.0-hd8ed1ab_0 \n", - " typing_extensions conda-forge/noarch::typing_extensions-4.11.0-pyha770c72_0 \n", - " tzcode conda-forge/linux-64::tzcode-2024a-h3f72095_0 \n", - " unicodedata2 conda-forge/linux-64::unicodedata2-15.1.0-py310h2372a71_0 \n", - " x264 conda-forge/linux-64::x264-1!164.3095-h166bdaf_2 \n", - " x265 conda-forge/linux-64::x265-3.5-h924138e_3 \n", - " xorg-fixesproto conda-forge/linux-64::xorg-fixesproto-5.0-h7f98852_1002 \n", - " xorg-kbproto conda-forge/linux-64::xorg-kbproto-1.0.7-h7f98852_1002 \n", - " xorg-libice conda-forge/linux-64::xorg-libice-1.1.1-hd590300_0 \n", - " xorg-libsm conda-forge/linux-64::xorg-libsm-1.2.4-h7391055_0 \n", - " xorg-libx11 conda-forge/linux-64::xorg-libx11-1.8.9-h8ee46fc_0 \n", - " xorg-libxau conda-forge/linux-64::xorg-libxau-1.0.11-hd590300_0 \n", - " xorg-libxdmcp conda-forge/linux-64::xorg-libxdmcp-1.1.3-h7f98852_0 \n", - " xorg-libxext conda-forge/linux-64::xorg-libxext-1.3.4-h0b41bf4_2 \n", - " xorg-libxfixes conda-forge/linux-64::xorg-libxfixes-5.0.3-h7f98852_1004 \n", - " xorg-libxrender conda-forge/linux-64::xorg-libxrender-0.9.11-hd590300_0 \n", - " xorg-renderproto conda-forge/linux-64::xorg-renderproto-0.11.1-h7f98852_1002 \n", - " xorg-xextproto conda-forge/linux-64::xorg-xextproto-7.3.0-h0b41bf4_1003 \n", - " xorg-xproto conda-forge/linux-64::xorg-xproto-7.0.31-h7f98852_1007 \n", - " yaml conda-forge/linux-64::yaml-0.2.5-h7f98852_2 \n", - " zipp conda-forge/noarch::zipp-3.17.0-pyhd8ed1ab_0 \n", - " zlib conda-forge/linux-64::zlib-1.2.13-hd590300_5 \n", - "\n", - "The following packages will be UPDATED:\n", - "\n", - " ca-certificates 2023.11.17-hbcca054_0 --> 2024.2.2-hbcca054_0 \n", - " certifi 2023.11.17-pyhd8ed1ab_0 --> 2024.2.2-pyhd8ed1ab_0 \n", - " openssl 3.2.0-hd590300_1 --> 3.2.1-hd590300_1 \n", - "\n", - "\n", - "\n", - "Downloading and Extracting Packages:\n", - "cudatoolkit-11.8.0 | 682.5 MB | : 0% 0/1 [00:00torch==2.1.0)\n", - " Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", - "Collecting MarkupSafe>=2.0 (from jinja2->torch==2.1.0)\n", - " Downloading MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.0 kB)\n", - "Collecting mpmath>=0.19 (from sympy->torch==2.1.0)\n", - " Downloading mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)\n", - "Downloading torch-2.1.0-cp310-cp310-manylinux1_x86_64.whl (670.2 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m670.2/670.2 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_nccl_cu12-2.18.1-py3-none-manylinux1_x86_64.whl (209.8 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m209.8/209.8 MB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading triton-2.1.0-0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (89.2 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m89.2/89.2 MB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading filelock-3.13.4-py3-none-any.whl (11 kB)\n", - "Downloading fsspec-2024.3.1-py3-none-any.whl (171 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m172.0/172.0 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading Jinja2-3.1.3-py3-none-any.whl (133 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.2/133.2 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading networkx-3.3-py3-none-any.whl (1.7 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading sympy-1.12-py3-none-any.whl (5.7 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.7/5.7 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)\n", - "Downloading mpmath-1.3.0-py3-none-any.whl (536 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.2/536.2 kB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: mpmath, sympy, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, networkx, MarkupSafe, fsspec, filelock, triton, nvidia-cusparse-cu12, nvidia-cudnn-cu12, jinja2, nvidia-cusolver-cu12, torch\n", - "Successfully installed MarkupSafe-2.1.5 filelock-3.13.4 fsspec-2024.3.1 jinja2-3.1.3 mpmath-1.3.0 networkx-3.3 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.18.1 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105 sympy-1.12 torch-2.1.0 triton-2.1.0\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCollecting tensorboard==2.16.2\n", - " Downloading tensorboard-2.16.2-py3-none-any.whl.metadata (1.6 kB)\n", - "Collecting absl-py>=0.4 (from tensorboard==2.16.2)\n", - " Downloading absl_py-2.1.0-py3-none-any.whl.metadata (2.3 kB)\n", - "Collecting grpcio>=1.48.2 (from tensorboard==2.16.2)\n", - " Downloading grpcio-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)\n", - "Collecting markdown>=2.6.8 (from tensorboard==2.16.2)\n", - " Downloading Markdown-3.6-py3-none-any.whl.metadata (7.0 kB)\n", - "Requirement already satisfied: numpy>=1.12.0 in /usr/local/lib/python3.10/site-packages (from tensorboard==2.16.2) (1.26.4)\n", - "Collecting protobuf!=4.24.0,>=3.19.6 (from tensorboard==2.16.2)\n", - " Downloading protobuf-5.26.1-cp37-abi3-manylinux2014_x86_64.whl.metadata (592 bytes)\n", - "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/site-packages (from tensorboard==2.16.2) (68.2.2)\n", - "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/site-packages (from tensorboard==2.16.2) (1.16.0)\n", - "Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard==2.16.2)\n", - " Downloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl.metadata (1.1 kB)\n", - "Collecting werkzeug>=1.0.1 (from tensorboard==2.16.2)\n", - " Downloading werkzeug-3.0.2-py3-none-any.whl.metadata (4.1 kB)\n", - "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/site-packages (from werkzeug>=1.0.1->tensorboard==2.16.2) (2.1.5)\n", - "Downloading tensorboard-2.16.2-py3-none-any.whl (5.5 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m22.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading absl_py-2.1.0-py3-none-any.whl (133 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.7/133.7 kB\u001b[0m \u001b[31m12.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading grpcio-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.5 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m58.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading Markdown-3.6-py3-none-any.whl (105 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.4/105.4 kB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading protobuf-5.26.1-cp37-abi3-manylinux2014_x86_64.whl (302 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.8/302.8 kB\u001b[0m \u001b[31m24.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl (6.6 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.6/6.6 MB\u001b[0m \u001b[31m63.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading werkzeug-3.0.2-py3-none-any.whl (226 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m226.8/226.8 kB\u001b[0m \u001b[31m20.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: werkzeug, tensorboard-data-server, protobuf, markdown, grpcio, absl-py, tensorboard\n", - "Successfully installed absl-py-2.1.0 grpcio-1.62.1 markdown-3.6 protobuf-5.26.1 tensorboard-2.16.2 tensorboard-data-server-0.7.2 werkzeug-3.0.2\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCollecting phonemizer==3.2.1\n", - " Downloading phonemizer-3.2.1-py3-none-any.whl.metadata (7.4 kB)\n", - "Requirement already satisfied: joblib in /usr/local/lib/python3.10/site-packages (from phonemizer==3.2.1) (1.4.0)\n", - "Collecting segments (from phonemizer==3.2.1)\n", - " Downloading segments-2.2.1-py2.py3-none-any.whl.metadata (3.3 kB)\n", - "Collecting attrs>=18.1 (from phonemizer==3.2.1)\n", - " Downloading attrs-23.2.0-py3-none-any.whl.metadata (9.5 kB)\n", - "Collecting dlinfo (from phonemizer==3.2.1)\n", - " Downloading dlinfo-1.2.1-py3-none-any.whl.metadata (1.1 kB)\n", - "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from phonemizer==3.2.1) (4.11.0)\n", - "Collecting clldutils>=1.7.3 (from segments->phonemizer==3.2.1)\n", - " Downloading clldutils-3.22.2-py2.py3-none-any.whl.metadata (3.0 kB)\n", - "Collecting csvw>=1.5.6 (from segments->phonemizer==3.2.1)\n", - " Downloading csvw-3.3.0-py2.py3-none-any.whl.metadata (10 kB)\n", - "Collecting regex (from segments->phonemizer==3.2.1)\n", - " Downloading regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m1.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: python-dateutil in /usr/local/lib/python3.10/site-packages (from clldutils>=1.7.3->segments->phonemizer==3.2.1) (2.9.0)\n", - "Collecting tabulate>=0.7.7 (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", - " Downloading tabulate-0.9.0-py3-none-any.whl.metadata (34 kB)\n", - "Collecting colorlog (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", - " Downloading colorlog-6.8.2-py3-none-any.whl.metadata (10 kB)\n", - "Collecting bibtexparser>=2.0.0b4 (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", - " Downloading bibtexparser-2.0.0b7-py3-none-any.whl.metadata (5.6 kB)\n", - "Collecting pylatexenc (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", - " Downloading pylatexenc-2.10.tar.gz (162 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m162.6/162.6 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Requirement already satisfied: markdown in /usr/local/lib/python3.10/site-packages (from clldutils>=1.7.3->segments->phonemizer==3.2.1) (3.6)\n", - "Collecting lxml (from clldutils>=1.7.3->segments->phonemizer==3.2.1)\n", - " Downloading lxml-5.2.1-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.4 kB)\n", - "Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/site-packages (from clldutils>=1.7.3->segments->phonemizer==3.2.1) (2.1.5)\n", - "Collecting babel (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading Babel-2.14.0-py3-none-any.whl.metadata (1.6 kB)\n", - "Requirement already satisfied: colorama in /usr/local/lib/python3.10/site-packages (from csvw>=1.5.6->segments->phonemizer==3.2.1) (0.4.6)\n", - "Collecting isodate (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading isodate-0.6.1-py2.py3-none-any.whl.metadata (9.6 kB)\n", - "Collecting jsonschema (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading jsonschema-4.21.1-py3-none-any.whl.metadata (7.8 kB)\n", - "Collecting language-tags (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading language_tags-1.2.0-py3-none-any.whl.metadata (2.1 kB)\n", - "Collecting rdflib (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading rdflib-7.0.0-py3-none-any.whl.metadata (11 kB)\n", - "Requirement already satisfied: requests in /usr/local/lib/python3.10/site-packages (from csvw>=1.5.6->segments->phonemizer==3.2.1) (2.31.0)\n", - "Collecting rfc3986<2 (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading rfc3986-1.5.0-py2.py3-none-any.whl.metadata (6.5 kB)\n", - "Collecting uritemplate>=3.0.0 (from csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading uritemplate-4.1.1-py2.py3-none-any.whl.metadata (2.9 kB)\n", - "Requirement already satisfied: six in /usr/local/lib/python3.10/site-packages (from isodate->csvw>=1.5.6->segments->phonemizer==3.2.1) (1.16.0)\n", - "Collecting jsonschema-specifications>=2023.03.6 (from jsonschema->csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading jsonschema_specifications-2023.12.1-py3-none-any.whl.metadata (3.0 kB)\n", - "Collecting referencing>=0.28.4 (from jsonschema->csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading referencing-0.34.0-py3-none-any.whl.metadata (2.8 kB)\n", - "Collecting rpds-py>=0.7.1 (from jsonschema->csvw>=1.5.6->segments->phonemizer==3.2.1)\n", - " Downloading rpds_py-0.18.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.1 kB)\n", - "Requirement already satisfied: pyparsing<4,>=2.1.0 in /usr/local/lib/python3.10/site-packages (from rdflib->csvw>=1.5.6->segments->phonemizer==3.2.1) (3.1.2)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (3.3.2)\n", - "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (3.6)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (2.1.0)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests->csvw>=1.5.6->segments->phonemizer==3.2.1) (2024.2.2)\n", - "Downloading phonemizer-3.2.1-py3-none-any.whl (90 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.6/90.6 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading attrs-23.2.0-py3-none-any.whl (60 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading dlinfo-1.2.1-py3-none-any.whl (3.6 kB)\n", - "Downloading segments-2.2.1-py2.py3-none-any.whl (15 kB)\n", - "Downloading clldutils-3.22.2-py2.py3-none-any.whl (1.7 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m15.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading csvw-3.3.0-py2.py3-none-any.whl (57 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.8/57.8 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (773 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m774.0/774.0 kB\u001b[0m \u001b[31m36.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading bibtexparser-2.0.0b7-py3-none-any.whl (38 kB)\n", - "Downloading rfc3986-1.5.0-py2.py3-none-any.whl (31 kB)\n", - "Downloading tabulate-0.9.0-py3-none-any.whl (35 kB)\n", - "Downloading uritemplate-4.1.1-py2.py3-none-any.whl (10 kB)\n", - "Downloading Babel-2.14.0-py3-none-any.whl (11.0 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.0/11.0 MB\u001b[0m \u001b[31m56.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading colorlog-6.8.2-py3-none-any.whl (11 kB)\n", - "Downloading isodate-0.6.1-py2.py3-none-any.whl (41 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.7/41.7 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading jsonschema-4.21.1-py3-none-any.whl (85 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.5/85.5 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading language_tags-1.2.0-py3-none-any.whl (213 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m213.4/213.4 kB\u001b[0m \u001b[31m19.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading lxml-5.2.1-cp310-cp310-manylinux_2_28_x86_64.whl (5.0 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.0/5.0 MB\u001b[0m \u001b[31m56.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading rdflib-7.0.0-py3-none-any.whl (531 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m531.9/531.9 kB\u001b[0m \u001b[31m42.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading jsonschema_specifications-2023.12.1-py3-none-any.whl (18 kB)\n", - "Downloading referencing-0.34.0-py3-none-any.whl (26 kB)\n", - "Downloading rpds_py-0.18.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.1 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m53.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hBuilding wheels for collected packages: pylatexenc\n", - " Building wheel for pylatexenc (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for pylatexenc: filename=pylatexenc-2.10-py3-none-any.whl size=136816 sha256=4c57cdcfd98c0a2de7a749fe90c9917f37213c2cd8423e01aeddd6a5b5438202\n", - " Stored in directory: /root/.cache/pip/wheels/d3/31/8b/e09b0386afd80cfc556c00408c9aeea5c35c4d484a9c762fd5\n", - "Successfully built pylatexenc\n", - "Installing collected packages: rfc3986, pylatexenc, language-tags, dlinfo, uritemplate, tabulate, rpds-py, regex, lxml, isodate, colorlog, bibtexparser, babel, attrs, referencing, rdflib, clldutils, jsonschema-specifications, jsonschema, csvw, segments, phonemizer\n", - "Successfully installed attrs-23.2.0 babel-2.14.0 bibtexparser-2.0.0b7 clldutils-3.22.2 colorlog-6.8.2 csvw-3.3.0 dlinfo-1.2.1 isodate-0.6.1 jsonschema-4.21.1 jsonschema-specifications-2023.12.1 language-tags-1.2.0 lxml-5.2.1 phonemizer-3.2.1 pylatexenc-2.10 rdflib-7.0.0 referencing-0.34.0 regex-2024.4.16 rfc3986-1.5.0 rpds-py-0.18.0 segments-2.2.1 tabulate-0.9.0 uritemplate-4.1.1\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCollecting torchaudio==2.1.0\n", - " Downloading torchaudio-2.1.0-cp310-cp310-manylinux1_x86_64.whl.metadata (5.7 kB)\n", - "Requirement already satisfied: torch==2.1.0 in /usr/local/lib/python3.10/site-packages (from torchaudio==2.1.0) (2.1.0)\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (3.13.4)\n", - "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (4.11.0)\n", - "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (1.12)\n", - "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (3.3)\n", - "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (3.1.3)\n", - "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (2024.3.1)\n", - "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (8.9.2.26)\n", - "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.3.1)\n", - "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (11.0.2.54)\n", - "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (10.3.2.106)\n", - "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (11.4.5.107)\n", - "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.0.106)\n", - "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (2.18.1)\n", - "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (12.1.105)\n", - "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchaudio==2.1.0) (2.1.0)\n", - "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.1.0->torchaudio==2.1.0) (12.4.127)\n", - "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/site-packages (from jinja2->torch==2.1.0->torchaudio==2.1.0) (2.1.5)\n", - "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch==2.1.0->torchaudio==2.1.0) (1.3.0)\n", - "Downloading torchaudio-2.1.0-cp310-cp310-manylinux1_x86_64.whl (3.3 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.3/3.3 MB\u001b[0m \u001b[31m14.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: torchaudio\n", - "Successfully installed torchaudio-2.1.0\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCollecting datasets==2.16.0\n", - " Downloading datasets-2.16.0-py3-none-any.whl.metadata (20 kB)\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (3.13.4)\n", - "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (1.26.4)\n", - "Collecting pyarrow>=8.0.0 (from datasets==2.16.0)\n", - " Downloading pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\n", - "Collecting pyarrow-hotfix (from datasets==2.16.0)\n", - " Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n", - "Collecting dill<0.3.8,>=0.3.0 (from datasets==2.16.0)\n", - " Downloading dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)\n", - "Requirement already satisfied: pandas in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (2.2.2)\n", - "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (2.31.0)\n", - "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (4.66.1)\n", - "Collecting xxhash (from datasets==2.16.0)\n", - " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n", - "Collecting multiprocess (from datasets==2.16.0)\n", - " Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n", - "Collecting fsspec<=2023.10.0,>=2023.1.0 (from fsspec[http]<=2023.10.0,>=2023.1.0->datasets==2.16.0)\n", - " Downloading fsspec-2023.10.0-py3-none-any.whl.metadata (6.8 kB)\n", - "Collecting aiohttp (from datasets==2.16.0)\n", - " Downloading aiohttp-3.9.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.5 kB)\n", - "Collecting huggingface-hub>=0.19.4 (from datasets==2.16.0)\n", - " Downloading huggingface_hub-0.22.2-py3-none-any.whl.metadata (12 kB)\n", - "Requirement already satisfied: packaging in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (23.2)\n", - "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/site-packages (from datasets==2.16.0) (6.0.1)\n", - "Collecting aiosignal>=1.1.2 (from aiohttp->datasets==2.16.0)\n", - " Downloading aiosignal-1.3.1-py3-none-any.whl.metadata (4.0 kB)\n", - "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/site-packages (from aiohttp->datasets==2.16.0) (23.2.0)\n", - "Collecting frozenlist>=1.1.1 (from aiohttp->datasets==2.16.0)\n", - " Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n", - "Collecting multidict<7.0,>=4.5 (from aiohttp->datasets==2.16.0)\n", - " Downloading multidict-6.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.2 kB)\n", - "Collecting yarl<2.0,>=1.0 (from aiohttp->datasets==2.16.0)\n", - " Downloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (31 kB)\n", - "Collecting async-timeout<5.0,>=4.0 (from aiohttp->datasets==2.16.0)\n", - " Downloading async_timeout-4.0.3-py3-none-any.whl.metadata (4.2 kB)\n", - "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/site-packages (from huggingface-hub>=0.19.4->datasets==2.16.0) (4.11.0)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (3.3.2)\n", - "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (3.6)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (2.1.0)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.16.0) (2024.2.2)\n", - "INFO: pip is looking at multiple versions of multiprocess to determine which version is compatible with other requirements. This could take a while.\n", - "Collecting multiprocess (from datasets==2.16.0)\n", - " Downloading multiprocess-0.70.15-py310-none-any.whl.metadata (7.2 kB)\n", - "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/site-packages (from pandas->datasets==2.16.0) (2.9.0)\n", - "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/site-packages (from pandas->datasets==2.16.0) (2024.1)\n", - "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/site-packages (from pandas->datasets==2.16.0) (2024.1)\n", - "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas->datasets==2.16.0) (1.16.0)\n", - "Downloading datasets-2.16.0-py3-none-any.whl (507 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading dill-0.3.7-py3-none-any.whl (115 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading fsspec-2023.10.0-py3-none-any.whl (166 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.4/166.4 kB\u001b[0m \u001b[31m14.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading aiohttp-3.9.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m19.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading huggingface_hub-0.22.2-py3-none-any.whl (388 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m388.9/388.9 kB\u001b[0m \u001b[31m31.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl (38.3 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m24.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n", - "Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m17.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n", - "Downloading async_timeout-4.0.3-py3-none-any.whl (5.7 kB)\n", - "Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (239 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m239.5/239.5 kB\u001b[0m \u001b[31m20.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading multidict-6.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (124 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.3/124.3 kB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (301 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m301.6/301.6 kB\u001b[0m \u001b[31m25.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: xxhash, pyarrow-hotfix, pyarrow, multidict, fsspec, frozenlist, dill, async-timeout, yarl, multiprocess, huggingface-hub, aiosignal, aiohttp, datasets\n", - " Attempting uninstall: fsspec\n", - " Found existing installation: fsspec 2024.3.1\n", - " Uninstalling fsspec-2024.3.1:\n", - " Successfully uninstalled fsspec-2024.3.1\n", - "Successfully installed aiohttp-3.9.5 aiosignal-1.3.1 async-timeout-4.0.3 datasets-2.16.0 dill-0.3.7 frozenlist-1.4.1 fsspec-2023.10.0 huggingface-hub-0.22.2 multidict-6.0.5 multiprocess-0.70.15 pyarrow-15.0.2 pyarrow-hotfix-0.6 xxhash-3.4.1 yarl-1.9.4\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCollecting torchmetrics==0.11.1\n", - " Downloading torchmetrics-0.11.1-py3-none-any.whl.metadata (16 kB)\n", - "Requirement already satisfied: numpy>=1.17.2 in /usr/local/lib/python3.10/site-packages (from torchmetrics==0.11.1) (1.26.4)\n", - "Requirement already satisfied: torch>=1.8.1 in /usr/local/lib/python3.10/site-packages (from torchmetrics==0.11.1) (2.1.0)\n", - "Requirement already satisfied: packaging in /usr/local/lib/python3.10/site-packages (from torchmetrics==0.11.1) (23.2)\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (3.13.4)\n", - "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (4.11.0)\n", - "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (1.12)\n", - "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (3.3)\n", - "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (3.1.3)\n", - "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (2023.10.0)\n", - "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", - "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (8.9.2.26)\n", - "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.3.1)\n", - "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (11.0.2.54)\n", - "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (10.3.2.106)\n", - "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (11.4.5.107)\n", - "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.0.106)\n", - "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (2.18.1)\n", - "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (12.1.105)\n", - "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch>=1.8.1->torchmetrics==0.11.1) (2.1.0)\n", - "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.8.1->torchmetrics==0.11.1) (12.4.127)\n", - "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/site-packages (from jinja2->torch>=1.8.1->torchmetrics==0.11.1) (2.1.5)\n", - "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch>=1.8.1->torchmetrics==0.11.1) (1.3.0)\n", - "Downloading torchmetrics-0.11.1-py3-none-any.whl (517 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m517.2/517.2 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: torchmetrics\n", - "Successfully installed torchmetrics-0.11.1\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCollecting torchvision==0.16.0\n", - " Downloading torchvision-0.16.0-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n", - "Requirement already satisfied: numpy in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (1.26.4)\n", - "Requirement already satisfied: requests in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (2.31.0)\n", - "Requirement already satisfied: torch==2.1.0 in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (2.1.0)\n", - "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/site-packages (from torchvision==0.16.0) (10.3.0)\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (3.13.4)\n", - "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (4.11.0)\n", - "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (1.12)\n", - "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (3.3)\n", - "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (3.1.3)\n", - "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (2023.10.0)\n", - "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (8.9.2.26)\n", - "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.3.1)\n", - "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (11.0.2.54)\n", - "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (10.3.2.106)\n", - "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (11.4.5.107)\n", - "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.0.106)\n", - "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (2.18.1)\n", - "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (12.1.105)\n", - "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->torchvision==0.16.0) (2.1.0)\n", - "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.1.0->torchvision==0.16.0) (12.4.127)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (3.3.2)\n", - "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (3.6)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (2.1.0)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests->torchvision==0.16.0) (2024.2.2)\n", - "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/site-packages (from jinja2->torch==2.1.0->torchvision==0.16.0) (2.1.5)\n", - "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch==2.1.0->torchvision==0.16.0) (1.3.0)\n", - "Downloading torchvision-0.16.0-cp310-cp310-manylinux1_x86_64.whl (6.9 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m22.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: torchvision\n", - "Successfully installed torchvision-0.16.0\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCollecting audiocraft\n", - " Cloning https://****@github.com/facebookresearch/audiocraft to /tmp/pip-install-kthaw99y/audiocraft_35cc3991adfe4664939ef82eecd3e7a1\n", - " Running command git clone --filter=blob:none --quiet 'https://****@github.com/facebookresearch/audiocraft' /tmp/pip-install-kthaw99y/audiocraft_35cc3991adfe4664939ef82eecd3e7a1\n", - " Resolved https://****@github.com/facebookresearch/audiocraft to commit 69fea8b290ad1b4b40d28f92d1dfc0ab01dbab85\n", - " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Collecting av (from audiocraft)\n", - " Downloading av-12.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.6 kB)\n", - "Collecting einops (from audiocraft)\n", - " Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)\n", - "Collecting flashy>=0.0.1 (from audiocraft)\n", - " Downloading flashy-0.0.2.tar.gz (72 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.4/72.4 kB\u001b[0m \u001b[31m1.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", - " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", - " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", - "Collecting hydra-core>=1.1 (from audiocraft)\n", - " Downloading hydra_core-1.3.2-py3-none-any.whl.metadata (5.5 kB)\n", - "Collecting hydra_colorlog (from audiocraft)\n", - " Downloading hydra_colorlog-1.2.0-py3-none-any.whl.metadata (949 bytes)\n", - "Collecting julius (from audiocraft)\n", - " Downloading julius-0.2.7.tar.gz (59 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.6/59.6 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Collecting num2words (from audiocraft)\n", - " Downloading num2words-0.5.13-py3-none-any.whl.metadata (12 kB)\n", - "Requirement already satisfied: numpy in /usr/local/lib/python3.10/site-packages (from audiocraft) (1.26.4)\n", - "Collecting sentencepiece (from audiocraft)\n", - " Downloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.7 kB)\n", - "Collecting spacy>=3.6.1 (from audiocraft)\n", - " Downloading spacy-3.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (27 kB)\n", - "Requirement already satisfied: torch==2.1.0 in /usr/local/lib/python3.10/site-packages (from audiocraft) (2.1.0)\n", - "Requirement already satisfied: torchaudio<2.1.2,>=2.0.0 in /usr/local/lib/python3.10/site-packages (from audiocraft) (2.1.0)\n", - "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/site-packages (from audiocraft) (0.22.2)\n", - "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/site-packages (from audiocraft) (4.66.1)\n", - "Collecting transformers>=4.31.0 (from audiocraft)\n", - " Downloading transformers-4.39.3-py3-none-any.whl.metadata (134 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m3.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hCollecting xformers<0.0.23 (from audiocraft)\n", - " Downloading xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl.metadata (1.0 kB)\n", - "Collecting demucs (from audiocraft)\n", - " Downloading demucs-4.0.1.tar.gz (1.2 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m14.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Requirement already satisfied: librosa in /usr/local/lib/python3.10/site-packages (from audiocraft) (0.10.1)\n", - "Collecting gradio (from audiocraft)\n", - " Downloading gradio-4.26.0-py3-none-any.whl.metadata (15 kB)\n", - "Requirement already satisfied: torchmetrics in /usr/local/lib/python3.10/site-packages (from audiocraft) (0.11.1)\n", - "Collecting encodec (from audiocraft)\n", - " Downloading encodec-0.1.1.tar.gz (3.7 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.7/3.7 MB\u001b[0m \u001b[31m43.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/site-packages (from audiocraft) (5.26.1)\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (3.13.4)\n", - "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (4.11.0)\n", - "Requirement already satisfied: sympy in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (1.12)\n", - "Requirement already satisfied: networkx in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (3.3)\n", - "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (3.1.3)\n", - "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (2023.10.0)\n", - "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", - "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (8.9.2.26)\n", - "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.3.1)\n", - "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (11.0.2.54)\n", - "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (10.3.2.106)\n", - "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (11.4.5.107)\n", - "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.0.106)\n", - "Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (2.18.1)\n", - "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (12.1.105)\n", - "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/site-packages (from torch==2.1.0->audiocraft) (2.1.0)\n", - "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.1.0->audiocraft) (12.4.127)\n", - "Collecting dora-search (from flashy>=0.0.1->audiocraft)\n", - " Downloading dora_search-0.1.12.tar.gz (87 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.1/87.1 kB\u001b[0m \u001b[31m8.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", - " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", - " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", - "Requirement already satisfied: colorlog in /usr/local/lib/python3.10/site-packages (from flashy>=0.0.1->audiocraft) (6.8.2)\n", - "Collecting omegaconf<2.4,>=2.2 (from hydra-core>=1.1->audiocraft)\n", - " Downloading omegaconf-2.3.0-py3-none-any.whl.metadata (3.9 kB)\n", - "Collecting antlr4-python3-runtime==4.9.* (from hydra-core>=1.1->audiocraft)\n", - " Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.0/117.0 kB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Requirement already satisfied: packaging in /usr/local/lib/python3.10/site-packages (from hydra-core>=1.1->audiocraft) (23.2)\n", - "Collecting spacy-legacy<3.1.0,>=3.0.11 (from spacy>=3.6.1->audiocraft)\n", - " Downloading spacy_legacy-3.0.12-py2.py3-none-any.whl.metadata (2.8 kB)\n", - "Collecting spacy-loggers<2.0.0,>=1.0.0 (from spacy>=3.6.1->audiocraft)\n", - " Downloading spacy_loggers-1.0.5-py3-none-any.whl.metadata (23 kB)\n", - "Collecting murmurhash<1.1.0,>=0.28.0 (from spacy>=3.6.1->audiocraft)\n", - " Downloading murmurhash-1.0.10-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.0 kB)\n", - "Collecting cymem<2.1.0,>=2.0.2 (from spacy>=3.6.1->audiocraft)\n", - " Downloading cymem-2.0.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (8.4 kB)\n", - "Collecting preshed<3.1.0,>=3.0.2 (from spacy>=3.6.1->audiocraft)\n", - " Downloading preshed-3.0.9-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.2 kB)\n", - "Collecting thinc<8.3.0,>=8.2.2 (from spacy>=3.6.1->audiocraft)\n", - " Downloading thinc-8.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (15 kB)\n", - "Collecting wasabi<1.2.0,>=0.9.1 (from spacy>=3.6.1->audiocraft)\n", - " Downloading wasabi-1.1.2-py3-none-any.whl.metadata (28 kB)\n", - "Collecting srsly<3.0.0,>=2.4.3 (from spacy>=3.6.1->audiocraft)\n", - " Downloading srsly-2.4.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (20 kB)\n", - "Collecting catalogue<2.1.0,>=2.0.6 (from spacy>=3.6.1->audiocraft)\n", - " Downloading catalogue-2.0.10-py3-none-any.whl.metadata (14 kB)\n", - "Collecting weasel<0.4.0,>=0.1.0 (from spacy>=3.6.1->audiocraft)\n", - " Downloading weasel-0.3.4-py3-none-any.whl.metadata (4.7 kB)\n", - "Collecting typer<0.10.0,>=0.3.0 (from spacy>=3.6.1->audiocraft)\n", - " Downloading typer-0.9.4-py3-none-any.whl.metadata (14 kB)\n", - "Collecting smart-open<7.0.0,>=5.2.1 (from spacy>=3.6.1->audiocraft)\n", - " Downloading smart_open-6.4.0-py3-none-any.whl.metadata (21 kB)\n", - "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/site-packages (from spacy>=3.6.1->audiocraft) (2.31.0)\n", - "Collecting pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 (from spacy>=3.6.1->audiocraft)\n", - " Downloading pydantic-2.7.0-py3-none-any.whl.metadata (103 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m103.4/103.4 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: setuptools in /usr/local/lib/python3.10/site-packages (from spacy>=3.6.1->audiocraft) (68.2.2)\n", - "Collecting langcodes<4.0.0,>=3.2.0 (from spacy>=3.6.1->audiocraft)\n", - " Downloading langcodes-3.3.0-py3-none-any.whl.metadata (29 kB)\n", - "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/site-packages (from transformers>=4.31.0->audiocraft) (6.0.1)\n", - "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/site-packages (from transformers>=4.31.0->audiocraft) (2024.4.16)\n", - "Collecting tokenizers<0.19,>=0.14 (from transformers>=4.31.0->audiocraft)\n", - " Downloading tokenizers-0.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n", - "Collecting safetensors>=0.4.1 (from transformers>=4.31.0->audiocraft)\n", - " Downloading safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n", - "Collecting lameenc>=1.2 (from demucs->audiocraft)\n", - " Downloading lameenc-1.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl.metadata (803 bytes)\n", - "Collecting openunmix (from demucs->audiocraft)\n", - " Downloading openunmix-1.3.0-py3-none-any.whl.metadata (17 kB)\n", - "Collecting aiofiles<24.0,>=22.0 (from gradio->audiocraft)\n", - " Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)\n", - "Collecting altair<6.0,>=4.2.0 (from gradio->audiocraft)\n", - " Downloading altair-5.3.0-py3-none-any.whl.metadata (9.2 kB)\n", - "Collecting fastapi (from gradio->audiocraft)\n", - " Downloading fastapi-0.110.1-py3-none-any.whl.metadata (24 kB)\n", - "Collecting ffmpy (from gradio->audiocraft)\n", - " Downloading ffmpy-0.3.2.tar.gz (5.5 kB)\n", - " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Collecting gradio-client==0.15.1 (from gradio->audiocraft)\n", - " Downloading gradio_client-0.15.1-py3-none-any.whl.metadata (7.1 kB)\n", - "Collecting httpx>=0.24.1 (from gradio->audiocraft)\n", - " Downloading httpx-0.27.0-py3-none-any.whl.metadata (7.2 kB)\n", - "Collecting importlib-resources<7.0,>=1.3 (from gradio->audiocraft)\n", - " Downloading importlib_resources-6.4.0-py3-none-any.whl.metadata (3.9 kB)\n", - "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (2.1.5)\n", - "Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (3.8.4)\n", - "Collecting orjson~=3.0 (from gradio->audiocraft)\n", - " Downloading orjson-3.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (49 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.7/49.7 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (2.2.2)\n", - "Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/site-packages (from gradio->audiocraft) (10.3.0)\n", - "Collecting pydub (from gradio->audiocraft)\n", - " Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n", - "Collecting python-multipart>=0.0.9 (from gradio->audiocraft)\n", - " Downloading python_multipart-0.0.9-py3-none-any.whl.metadata (2.5 kB)\n", - "Collecting ruff>=0.2.2 (from gradio->audiocraft)\n", - " Downloading ruff-0.3.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (23 kB)\n", - "Collecting semantic-version~=2.0 (from gradio->audiocraft)\n", - " Downloading semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n", - "Collecting tomlkit==0.12.0 (from gradio->audiocraft)\n", - " Downloading tomlkit-0.12.0-py3-none-any.whl.metadata (2.7 kB)\n", - "Collecting uvicorn>=0.14.0 (from gradio->audiocraft)\n", - " Downloading uvicorn-0.29.0-py3-none-any.whl.metadata (6.3 kB)\n", - "Collecting websockets<12.0,>=10.0 (from gradio-client==0.15.1->gradio->audiocraft)\n", - " Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)\n", - "Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (3.0.1)\n", - "Requirement already satisfied: scipy>=1.2.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.13.0)\n", - "Requirement already satisfied: scikit-learn>=0.20.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.2.2)\n", - "Requirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.4.0)\n", - "Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (5.1.1)\n", - "Requirement already satisfied: numba>=0.51.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.59.1)\n", - "Requirement already satisfied: soundfile>=0.12.1 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.12.1)\n", - "Requirement already satisfied: pooch>=1.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.8.1)\n", - "Requirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.3.7)\n", - "Requirement already satisfied: lazy-loader>=0.1 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (0.4)\n", - "Requirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.10/site-packages (from librosa->audiocraft) (1.0.7)\n", - "Collecting docopt>=0.6.2 (from num2words->audiocraft)\n", - " Downloading docopt-0.6.2.tar.gz (25 kB)\n", - " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/site-packages (from altair<6.0,>=4.2.0->gradio->audiocraft) (4.21.1)\n", - "Collecting toolz (from altair<6.0,>=4.2.0->gradio->audiocraft)\n", - " Downloading toolz-0.12.1-py3-none-any.whl.metadata (5.1 kB)\n", - "Collecting anyio (from httpx>=0.24.1->gradio->audiocraft)\n", - " Downloading anyio-4.3.0-py3-none-any.whl.metadata (4.6 kB)\n", - "Requirement already satisfied: certifi in /usr/local/lib/python3.10/site-packages (from httpx>=0.24.1->gradio->audiocraft) (2024.2.2)\n", - "Collecting httpcore==1.* (from httpx>=0.24.1->gradio->audiocraft)\n", - " Downloading httpcore-1.0.5-py3-none-any.whl.metadata (20 kB)\n", - "Requirement already satisfied: idna in /usr/local/lib/python3.10/site-packages (from httpx>=0.24.1->gradio->audiocraft) (3.6)\n", - "Collecting sniffio (from httpx>=0.24.1->gradio->audiocraft)\n", - " Downloading sniffio-1.3.1-py3-none-any.whl.metadata (3.9 kB)\n", - "Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx>=0.24.1->gradio->audiocraft)\n", - " Downloading h11-0.14.0-py3-none-any.whl.metadata (8.2 kB)\n", - "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (1.2.1)\n", - "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (0.12.1)\n", - "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (4.51.0)\n", - "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (1.4.5)\n", - "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (3.1.2)\n", - "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/site-packages (from matplotlib~=3.0->gradio->audiocraft) (2.9.0)\n", - "Requirement already satisfied: llvmlite<0.43,>=0.42.0dev0 in /usr/local/lib/python3.10/site-packages (from numba>=0.51.0->librosa->audiocraft) (0.42.0)\n", - "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/site-packages (from pandas<3.0,>=1.0->gradio->audiocraft) (2024.1)\n", - "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/site-packages (from pandas<3.0,>=1.0->gradio->audiocraft) (2024.1)\n", - "Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.10/site-packages (from pooch>=1.0->librosa->audiocraft) (4.1.0)\n", - "Collecting annotated-types>=0.4.0 (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.6.1->audiocraft)\n", - " Downloading annotated_types-0.6.0-py3-none-any.whl.metadata (12 kB)\n", - "Collecting pydantic-core==2.18.1 (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.6.1->audiocraft)\n", - " Downloading pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.5 kB)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy>=3.6.1->audiocraft) (3.3.2)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy>=3.6.1->audiocraft) (2.1.0)\n", - "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/site-packages (from scikit-learn>=0.20.0->librosa->audiocraft) (3.4.0)\n", - "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/site-packages (from soundfile>=0.12.1->librosa->audiocraft) (1.16.0)\n", - "Collecting blis<0.8.0,>=0.7.8 (from thinc<8.3.0,>=8.2.2->spacy>=3.6.1->audiocraft)\n", - " Downloading blis-0.7.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.4 kB)\n", - "Collecting confection<1.0.0,>=0.0.1 (from thinc<8.3.0,>=8.2.2->spacy>=3.6.1->audiocraft)\n", - " Downloading confection-0.1.4-py3-none-any.whl.metadata (19 kB)\n", - "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.10/site-packages (from typer<0.10.0,>=0.3.0->spacy>=3.6.1->audiocraft) (8.1.7)\n", - "Requirement already satisfied: colorama<0.5.0,>=0.4.3 in /usr/local/lib/python3.10/site-packages (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (0.4.6)\n", - "Collecting shellingham<2.0.0,>=1.3.0 (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft)\n", - " Downloading shellingham-1.5.4-py2.py3-none-any.whl.metadata (3.5 kB)\n", - "Requirement already satisfied: rich<14.0.0,>=10.11.0 in /usr/local/lib/python3.10/site-packages (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (13.7.1)\n", - "Collecting cloudpathlib<0.17.0,>=0.7.0 (from weasel<0.4.0,>=0.1.0->spacy>=3.6.1->audiocraft)\n", - " Downloading cloudpathlib-0.16.0-py3-none-any.whl.metadata (14 kB)\n", - "Collecting retrying (from dora-search->flashy>=0.0.1->audiocraft)\n", - " Downloading retrying-1.3.4-py3-none-any.whl.metadata (6.9 kB)\n", - "Collecting submitit (from dora-search->flashy>=0.0.1->audiocraft)\n", - " Downloading submitit-1.5.1-py3-none-any.whl.metadata (8.0 kB)\n", - "Collecting treetable (from dora-search->flashy>=0.0.1->audiocraft)\n", - " Downloading treetable-0.2.5.tar.gz (10 kB)\n", - " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - "Collecting starlette<0.38.0,>=0.37.2 (from fastapi->gradio->audiocraft)\n", - " Downloading starlette-0.37.2-py3-none-any.whl.metadata (5.9 kB)\n", - "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/site-packages (from sympy->torch==2.1.0->audiocraft) (1.3.0)\n", - "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/site-packages (from cffi>=1.0->soundfile>=0.12.1->librosa->audiocraft) (2.21)\n", - "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (23.2.0)\n", - "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (2023.12.1)\n", - "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (0.34.0)\n", - "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio->audiocraft) (0.18.0)\n", - "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio->audiocraft) (1.16.0)\n", - "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/site-packages (from rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (3.0.0)\n", - "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/site-packages (from rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (2.17.2)\n", - "Collecting exceptiongroup>=1.0.2 (from anyio->httpx>=0.24.1->gradio->audiocraft)\n", - " Downloading exceptiongroup-1.2.0-py3-none-any.whl.metadata (6.6 kB)\n", - "Collecting cloudpickle>=1.2.1 (from submitit->dora-search->flashy>=0.0.1->audiocraft)\n", - " Downloading cloudpickle-3.0.0-py3-none-any.whl.metadata (7.0 kB)\n", - "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/site-packages (from markdown-it-py>=2.2.0->rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio->audiocraft) (0.1.2)\n", - "Downloading hydra_core-1.3.2-py3-none-any.whl (154 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.5/154.5 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading spacy-3.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (6.6 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.6/6.6 MB\u001b[0m \u001b[31m49.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading transformers-4.39.3-py3-none-any.whl (8.8 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m67.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl (211.8 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.8/211.8 MB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading av-12.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (33.8 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m33.8/33.8 MB\u001b[0m \u001b[31m35.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading einops-0.7.0-py3-none-any.whl (44 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading gradio-4.26.0-py3-none-any.whl (17.1 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.1/17.1 MB\u001b[0m \u001b[31m49.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading gradio_client-0.15.1-py3-none-any.whl (313 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m313.6/313.6 kB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n", - "Downloading hydra_colorlog-1.2.0-py3-none-any.whl (3.6 kB)\n", - "Downloading num2words-0.5.13-py3-none-any.whl (143 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m143.3/143.3 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m51.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n", - "Downloading altair-5.3.0-py3-none-any.whl (857 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m857.8/857.8 kB\u001b[0m \u001b[31m43.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading catalogue-2.0.10-py3-none-any.whl (17 kB)\n", - "Downloading cymem-2.0.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (46 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.1/46.1 kB\u001b[0m \u001b[31m4.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading httpx-0.27.0-py3-none-any.whl (75 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m7.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading importlib_resources-6.4.0-py3-none-any.whl (38 kB)\n", - "Downloading lameenc-1.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl (239 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m239.8/239.8 kB\u001b[0m \u001b[31m21.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading langcodes-3.3.0-py3-none-any.whl (181 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m181.6/181.6 kB\u001b[0m \u001b[31m15.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading murmurhash-1.0.10-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (29 kB)\n", - "Downloading omegaconf-2.3.0-py3-none-any.whl (79 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.5/79.5 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading orjson-3.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (141 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m141.1/141.1 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading preshed-3.0.9-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (156 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m156.9/156.9 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading pydantic-2.7.0-py3-none-any.whl (407 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m407.9/407.9 kB\u001b[0m \u001b[31m32.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m54.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n", - "Downloading ruff-0.3.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.9 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.9/8.9 MB\u001b[0m \u001b[31m56.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m49.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n", - "Downloading smart_open-6.4.0-py3-none-any.whl (57 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.0/57.0 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading spacy_legacy-3.0.12-py2.py3-none-any.whl (29 kB)\n", - "Downloading spacy_loggers-1.0.5-py3-none-any.whl (22 kB)\n", - "Downloading srsly-2.4.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (493 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m493.0/493.0 kB\u001b[0m \u001b[31m29.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading thinc-8.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (922 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m922.3/922.3 kB\u001b[0m \u001b[31m46.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading tokenizers-0.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m54.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading typer-0.9.4-py3-none-any.whl (45 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading uvicorn-0.29.0-py3-none-any.whl (60 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading wasabi-1.1.2-py3-none-any.whl (27 kB)\n", - "Downloading weasel-0.3.4-py3-none-any.whl (50 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.1/50.1 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading fastapi-0.110.1-py3-none-any.whl (91 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.9/91.9 kB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading openunmix-1.3.0-py3-none-any.whl (40 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.0/40.0 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n", - "Downloading annotated_types-0.6.0-py3-none-any.whl (12 kB)\n", - "Downloading blis-0.7.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.2 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.2/10.2 MB\u001b[0m \u001b[31m54.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading cloudpathlib-0.16.0-py3-none-any.whl (45 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.0/45.0 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading confection-0.1.4-py3-none-any.whl (35 kB)\n", - "Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n", - "Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading anyio-4.3.0-py3-none-any.whl (85 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.6/85.6 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading sniffio-1.3.1-py3-none-any.whl (10 kB)\n", - "Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading retrying-1.3.4-py3-none-any.whl (11 kB)\n", - "Downloading submitit-1.5.1-py3-none-any.whl (74 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m74.7/74.7 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading toolz-0.12.1-py3-none-any.whl (56 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.1/56.1 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading cloudpickle-3.0.0-py3-none-any.whl (20 kB)\n", - "Downloading exceptiongroup-1.2.0-py3-none-any.whl (16 kB)\n", - "Building wheels for collected packages: audiocraft, flashy, antlr4-python3-runtime, demucs, julius, encodec, docopt, dora-search, ffmpy, treetable\n", - " Building wheel for audiocraft (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for audiocraft: filename=audiocraft-1.3.0a1-py3-none-any.whl size=264806 sha256=7a718f3484e2f14f82562388442c366616e7252ffda2824e4ea16ffe449601cb\n", - " Stored in directory: /tmp/pip-ephem-wheel-cache-7svi6_32/wheels/61/bb/15/cf53514254501b4472fb64d137bd3ab88737daf6917dfcbdc9\n", - " Building wheel for flashy (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for flashy: filename=flashy-0.0.2-py3-none-any.whl size=34527 sha256=c684f44a995181f7bf4d39852fd2961bc695a0dd8618116d2ddee969908fd23e\n", - " Stored in directory: /root/.cache/pip/wheels/07/bd/3d/16c6bc059203299f37b6014643b739afb7f6d1be13a94fc2f7\n", - " Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for antlr4-python3-runtime: filename=antlr4_python3_runtime-4.9.3-py3-none-any.whl size=144554 sha256=882304c91af3c0fe39ed685f7ee9a3142d860ada9311dd2512a5bf5289e4c764\n", - " Stored in directory: /root/.cache/pip/wheels/12/93/dd/1f6a127edc45659556564c5730f6d4e300888f4bca2d4c5a88\n", - " Building wheel for demucs (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for demucs: filename=demucs-4.0.1-py3-none-any.whl size=78391 sha256=9bf9cafaf6fbcf260534861b3513e131f3a1ba0bb5af6930af9ebe97783a2fb5\n", - " Stored in directory: /root/.cache/pip/wheels/2a/65/a1/6cc0e525a84375af3b09823b3326b0ece53c4e68302c054548\n", - " Building wheel for julius (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for julius: filename=julius-0.2.7-py3-none-any.whl size=21870 sha256=de9d763ebd7f85a5ad43ec67b005b190d336eded70e3b2afe487c62f278c5939\n", - " Stored in directory: /root/.cache/pip/wheels/b9/b2/05/f883527ffcb7f2ead5438a2c23439aa0c881eaa9a4c80256f4\n", - " Building wheel for encodec (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for encodec: filename=encodec-0.1.1-py3-none-any.whl size=45759 sha256=0af63d8afea5a09bacc48f6fa2767e53d732883c98e862d8904d608531bae959\n", - " Stored in directory: /root/.cache/pip/wheels/fc/36/cb/81af8b985a5f5e0815312d5e52b41263237af07b977e6bcbf3\n", - " Building wheel for docopt (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=61388c7fb75041fc6643e6a8638dd74b74bba5dbbb58484a48ffafcee94744ca\n", - " Stored in directory: /root/.cache/pip/wheels/fc/ab/d4/5da2067ac95b36618c629a5f93f809425700506f72c9732fac\n", - " Building wheel for dora-search (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for dora-search: filename=dora_search-0.1.12-py3-none-any.whl size=75093 sha256=f3392d966ef342611ed2a3ebdfcd5b17ef4659bac57a6848084af79a88665e54\n", - " Stored in directory: /root/.cache/pip/wheels/b1/c2/c0/bea5cc405497284d584b958f293ef32c23bad42ae5e44d973c\n", - " Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for ffmpy: filename=ffmpy-0.3.2-py3-none-any.whl size=5584 sha256=54a8e3c6638890205277f5d18ff56d1da1ed9147bc10b2a26eb32af1e7b860bb\n", - " Stored in directory: /root/.cache/pip/wheels/bd/65/9a/671fc6dcde07d4418df0c592f8df512b26d7a0029c2a23dd81\n", - " Building wheel for treetable (setup.py) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for treetable: filename=treetable-0.2.5-py3-none-any.whl size=7333 sha256=51072008b023f976ac4932d447b9fdc088156bb7918ae05caada65a1fabbc9f5\n", - " Stored in directory: /root/.cache/pip/wheels/72/55/0e/91c3655bdb162446f8a7cd477579397544454a63ae7c599c0c\n", - "Successfully built audiocraft flashy antlr4-python3-runtime demucs julius encodec docopt dora-search ffmpy treetable\n", - "Installing collected packages: sentencepiece, pydub, lameenc, ffmpy, docopt, cymem, antlr4-python3-runtime, websockets, wasabi, typer, treetable, toolz, tomlkit, spacy-loggers, spacy-legacy, sniffio, smart-open, shellingham, semantic-version, safetensors, ruff, retrying, python-multipart, pydantic-core, orjson, omegaconf, num2words, murmurhash, langcodes, importlib-resources, h11, exceptiongroup, einops, cloudpickle, cloudpathlib, catalogue, blis, av, annotated-types, aiofiles, uvicorn, submitit, srsly, pydantic, preshed, hydra-core, httpcore, anyio, tokenizers, starlette, hydra_colorlog, httpx, confection, xformers, weasel, transformers, thinc, julius, gradio-client, fastapi, dora-search, altair, spacy, openunmix, gradio, flashy, encodec, demucs, audiocraft\n", - "Successfully installed aiofiles-23.2.1 altair-5.3.0 annotated-types-0.6.0 antlr4-python3-runtime-4.9.3 anyio-4.3.0 audiocraft-1.3.0a1 av-12.0.0 blis-0.7.11 catalogue-2.0.10 cloudpathlib-0.16.0 cloudpickle-3.0.0 confection-0.1.4 cymem-2.0.8 demucs-4.0.1 docopt-0.6.2 dora-search-0.1.12 einops-0.7.0 encodec-0.1.1 exceptiongroup-1.2.0 fastapi-0.110.1 ffmpy-0.3.2 flashy-0.0.2 gradio-4.26.0 gradio-client-0.15.1 h11-0.14.0 httpcore-1.0.5 httpx-0.27.0 hydra-core-1.3.2 hydra_colorlog-1.2.0 importlib-resources-6.4.0 julius-0.2.7 lameenc-1.7.0 langcodes-3.3.0 murmurhash-1.0.10 num2words-0.5.13 omegaconf-2.3.0 openunmix-1.3.0 orjson-3.10.1 preshed-3.0.9 pydantic-2.7.0 pydantic-core-2.18.1 pydub-0.25.1 python-multipart-0.0.9 retrying-1.3.4 ruff-0.3.7 safetensors-0.4.3 semantic-version-2.10.0 sentencepiece-0.2.0 shellingham-1.5.4 smart-open-6.4.0 sniffio-1.3.1 spacy-3.7.4 spacy-legacy-3.0.12 spacy-loggers-1.0.5 srsly-2.4.8 starlette-0.37.2 submitit-1.5.1 thinc-8.2.3 tokenizers-0.15.2 tomlkit-0.12.0 toolz-0.12.1 transformers-4.39.3 treetable-0.2.5 typer-0.9.4 uvicorn-0.29.0 wasabi-1.1.2 weasel-0.3.4 websockets-11.0.3 xformers-0.0.22.post7\n", - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n", - "\u001b[0mCloning into 'VoiceCraft'...\n", - "remote: Enumerating objects: 340, done.\u001b[K\n", - "remote: Counting objects: 100% (123/123), done.\u001b[K\n", - "remote: Compressing objects: 100% (57/57), done.\u001b[K\n", - "remote: Total 340 (delta 91), reused 76 (delta 66), pack-reused 217\u001b[K\n", - "Receiving objects: 100% (340/340), 2.47 MiB | 12.88 MiB/s, done.\n", - "Resolving deltas: 100% (198/198), done.\n" - ] - } - ] - }, - { - "cell_type": "code", - "source": [ - "!mfa model download dictionary english_us_arpa && \\\n", - "mfa model download acoustic english_us_arpa\n" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "8pknHCCM5Umj", - "outputId": "149bfa85-96fe-4383-a5f0-a8e92c4dca26" - }, - "execution_count": 3, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "\u001b[2;36m \u001b[0m\u001b[32mINFO \u001b[0m Saved model to \u001b[35m/root/Documents/MFA/pretrained_models/dictionary/\u001b[0m\u001b[95menglish_us_arpa.dict\u001b[0m, you \n", - "\u001b[2;36m \u001b[0m can now use english_us_arpa in place of dictionary paths in mfa commands. \n", - "\u001b[2;36m \u001b[0m\u001b[32mINFO \u001b[0m Saved model to \u001b[35m/root/Documents/MFA/pretrained_models/acoustic/\u001b[0m\u001b[95menglish_us_arpa.zip\u001b[0m, you can\n", - "\u001b[2;36m \u001b[0m now use english_us_arpa in place of acoustic paths in mfa commands. \n" - ] - } - ] - }, - { - "cell_type": "code", - "source": [ - "# simply installing audiocraft breaks due to no config, so move the default into site-packages\n", - "%cd /content/VoiceCraft\n", - "!git clone https://github.com/facebookresearch/audiocraft.git\n", - "!mv audiocraft/config /usr/local/lib/python3.10/site-packages/\n", - "!rm -rf audiocraft" - ], + "execution_count": 5, "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "Wdn4Hj9Z5ZbW", - "outputId": "4eb6db4b-e6de-4bd3-a8a3-586ada896145" + "id": "SiWiiUpv5iQg" }, - "execution_count": 4, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "/content/VoiceCraft\n", - "Cloning into 'audiocraft'...\n", - "remote: Enumerating objects: 1426, done.\u001b[K\n", - "remote: Total 1426 (delta 0), reused 0 (delta 0), pack-reused 1426\u001b[K\n", - "Receiving objects: 100% (1426/1426), 1.95 MiB | 10.41 MiB/s, done.\n", - "Resolving deltas: 100% (802/802), done.\n" - ] - } - ] - }, - { - "cell_type": "code", + "outputs": [], "source": [ "# import libs\n", "import torch\n", @@ -3994,15 +24,15 @@ ")\n", "\n", "from models import voicecraft" - ], - "metadata": { - "id": "SiWiiUpv5iQg" - }, - "execution_count": 5, - "outputs": [] + ] }, { "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "a0pIv_pA5k0C" + }, + "outputs": [], "source": [ "# hyperparameters for inference\n", "left_margin = 0.08\n", @@ -4049,15 +79,15 @@ "audio_fn = f\"{temp_folder}/{filename}.wav\"\n", "transcript_fn = f\"{temp_folder}/{filename}.txt\"\n", "align_fn = f\"{align_temp}/{filename}.csv\"" - ], - "metadata": { - "id": "a0pIv_pA5k0C" - }, - "execution_count": 6, - "outputs": [] + ] }, { "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "iIPNTtibF4OL" + }, + "outputs": [], "source": [ "def get_mask_interval(ali_fn, word_span_ind, editType):\n", " with open(ali_fn, \"r\") as rf:\n", @@ -4080,15 +110,20 @@ " assert start != None\n", " break\n", " return (start, end)\n" - ], - "metadata": { - "id": "iIPNTtibF4OL" - }, - "execution_count": 9, - "outputs": [] + ] }, { "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 280 + }, + "id": "krbq1mBM6GDE", + "outputId": "d9267aef-05b2-4276-ee8b-5687cab5c612" + }, + "outputs": [], "source": [ "# propose what do you want the target modified transcript to be\n", "orig_transcript = \"But when I had approached so near to them which the sense deceives, Lost not by distance any of its marks,\"\n", @@ -4195,85 +230,23 @@ "# # pip uninstall Pillow\n", "# # pip install Pillow\n", "# # you are likely to get warning looks like WARNING:phonemizer:words count mismatch on 300.0% of the lines (3/1), this can be safely ignored" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 280 - }, - "id": "krbq1mBM6GDE", - "outputId": "d9267aef-05b2-4276-ee8b-5687cab5c612" - }, - "execution_count": 13, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "['deletion']\n", - "orig_span: [[7, 8]]\n", - "new_span: [[6, 7]]\n", - "intervals: [1.91] [2.42]\n" - ] - }, - { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\n", - " warnings.warn(\"torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\")\n", - "WARNING:phonemizer:words count mismatch on 200.0% of the lines (2/1)\n" - ] - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "original:\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "" - ], - "text/html": [ - "\n", - " \n", - " " - ] - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "edited:\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "" - ], - "text/html": [ - "\n", - " \n", - " " - ] - }, - "metadata": {} - } ] } - ] -} \ No newline at end of file + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "gpuType": "T4", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} From 73fac7c460188e160390acd124ad498d7dd55801 Mon Sep 17 00:00:00 2001 From: Pranay Gosar Date: Wed, 17 Apr 2024 12:37:14 -0500 Subject: [PATCH 3/8] move import up --- inference_speech_editing.ipynb | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/inference_speech_editing.ipynb b/inference_speech_editing.ipynb index 588d91a..90cd0de 100644 --- a/inference_speech_editing.ipynb +++ b/inference_speech_editing.ipynb @@ -23,7 +23,8 @@ " TextTokenizer,\n", ")\n", "\n", - "from models import voicecraft" + "from models import voicecraft\n", + "from edit_utils import parse_edit, get_edits" ] }, { @@ -129,8 +130,6 @@ "orig_transcript = \"But when I had approached so near to them which the sense deceives, Lost not by distance any of its marks,\"\n", "target_transcript = \"But when I had approached so near which the sense deceives, Lost not by distance any of its marks,\" # deletes \"to them\"\n", "\n", - "from edit_utils import parse_edit, get_edits\n", - "\n", "# run the script to turn user input to the format that the model can take\n", "operations, orig_span, new_span = parse_edit(orig_transcript, target_transcript)\n", "\n", From 8814295e980801172225267e96d17c0401e8a383 Mon Sep 17 00:00:00 2001 From: Pranay Gosar Date: Wed, 17 Apr 2024 19:01:39 -0500 Subject: [PATCH 4/8] fix overlapping margins --- inference_speech_editing.ipynb | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/inference_speech_editing.ipynb b/inference_speech_editing.ipynb index 90cd0de..eb8b31a 100644 --- a/inference_speech_editing.ipynb +++ b/inference_speech_editing.ipynb @@ -38,6 +38,7 @@ "# hyperparameters for inference\n", "left_margin = 0.08\n", "right_margin = 0.08\n", + "sub_amount = 0.01\n", "codec_audio_sr = 16000\n", "codec_sr = 50\n", "top_k = 0\n", @@ -128,13 +129,15 @@ "source": [ "# propose what do you want the target modified transcript to be\n", "orig_transcript = \"But when I had approached so near to them which the sense deceives, Lost not by distance any of its marks,\"\n", - "target_transcript = \"But when I had approached so near which the sense deceives, Lost not by distance any of its marks,\" # deletes \"to them\"\n", + "target_transcript = \"But I did approached so near to them which the sense deceives, Lost not by distance any of its marks,\"\n", + "\n", + "# from edit_utils import parse_edit, get_edits\n", "\n", "# run the script to turn user input to the format that the model can take\n", "operations, orig_span, new_span = parse_edit(orig_transcript, target_transcript)\n", "\n", "used_edits = get_edits(operations)\n", - "print(used_edits)\n", + "print(used_edits) \n", "\n", "def process_span(span):\n", " if span[0] > span[1]:\n", @@ -158,15 +161,28 @@ " starting_intervals.append(start)\n", " ending_intervals.append(end)\n", "\n", - "print(\"intervals: \", starting_intervals, ending_intervals)\n", - "\n", "info = torchaudio.info(audio_fn)\n", "audio_dur = info.num_frames / info.sample_rate\n", - "morphed_span = [(max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur))\n", - " for start, end in zip(starting_intervals, ending_intervals)] # in seconds\n", + "\n", + "def resolve_overlap(starting_intervals, ending_intervals, audio_dur, codec_sr, left_margin, right_margin, sub_amount):\n", + " while True:\n", + " morphed_span = [(max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur))\n", + " for start, end in zip(starting_intervals, ending_intervals)] # in seconds\n", + " mask_interval = [[round(span[0]*codec_sr), round(span[1]*codec_sr)] for span in morphed_span]\n", + " # Check for overlap\n", + " overlapping = any(a[1] >= b[0] for a, b in zip(mask_interval, mask_interval[1:]))\n", + " if not overlapping:\n", + " break\n", + " \n", + " # Reduce margins\n", + " left_margin -= sub_amount\n", + " right_margin -= sub_amount\n", + " \n", + " return mask_interval\n", + "\n", "\n", "# span in codec frames\n", - "mask_interval = [[round(span[0]*codec_sr), round(span[1]*codec_sr)] for span in morphed_span]\n", + "mask_interval = resolve_overlap(starting_intervals, ending_intervals, audio_dur, codec_sr, left_margin, right_margin, sub_amount)\n", "mask_interval = torch.LongTensor(mask_interval) # [M,2], M==1 for now\n", "\n", "# load model, tokenizer, and other necessary files\n", From 00d1b11a133717dafbd5459e15cb9d840d805110 Mon Sep 17 00:00:00 2001 From: Pranay Gosar Date: Sun, 5 May 2024 16:04:32 -0500 Subject: [PATCH 5/8] fix syntax error --- inference_speech_editing.ipynb | 1 + 1 file changed, 1 insertion(+) diff --git a/inference_speech_editing.ipynb b/inference_speech_editing.ipynb index dacf232..675c7a7 100644 --- a/inference_speech_editing.ipynb +++ b/inference_speech_editing.ipynb @@ -487,3 +487,4 @@ "nbformat": 4, "nbformat_minor": 0 } +} \ No newline at end of file From dc2239c58b41b13bfef515282c6677645732dd70 Mon Sep 17 00:00:00 2001 From: Pranay Gosar Date: Sun, 5 May 2024 17:20:49 -0500 Subject: [PATCH 6/8] add runtime error and fix merge regressions --- inference_speech_editing.ipynb | 406 +++++++-------------------------- 1 file changed, 85 insertions(+), 321 deletions(-) diff --git a/inference_speech_editing.ipynb b/inference_speech_editing.ipynb index 675c7a7..0abcb59 100644 --- a/inference_speech_editing.ipynb +++ b/inference_speech_editing.ipynb @@ -2,68 +2,54 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": 24, "metadata": {}, "outputs": [], - "source": [ - "import os\n", - "os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\" \n", - "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"7\"\n", - "os.environ[\"USER\"] = \"YOUR_USERNAME\" # TODO change this to your username" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/pyp/miniconda3/envs/voicecraft/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", - " from .autonotebook import tqdm as notebook_tqdm\n" - ] - } - ], "source": [ "# import libs\n", "import torch\n", "import torchaudio\n", + "import os\n", "import numpy as np\n", "import random\n", - "from argparse import Namespace\n", + "os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\"\n", + "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"0\"\n", + "os.environ[\"USER\"] = \"YOUR_USERNAME\" # TODO change this to your username\n", "\n", "from data.tokenizer import (\n", " AudioTokenizer,\n", " TextTokenizer,\n", ")\n", + "from inference_speech_editing_scale import get_mask_interval, inference_one_sample\n", + "from edit_utils import get_edits, parse_edit\n", "\n", + "from argparse import Namespace\n", "from models import voicecraft" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# install MFA models and dictionaries if you haven't done so already\n", - "!source ~/.bashrc && \\\n", - " conda activate voicecraft && \\\n", - " mfa model download dictionary english_us_arpa && \\\n", - " mfa model download acoustic english_us_arpa" + "# !source ~/.bashrc && \\\n", + "# conda activate voicecraft && \\\n", + "# mfa model download dictionary english_us_arpa && \\\n", + "# mfa model download acoustic english_us_arpa" ] }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# hyperparameters for inference\n", "left_margin = 0.08\n", "right_margin = 0.08\n", + "sub_amount = 0.01\n", "codec_audio_sr = 16000\n", "codec_sr = 50\n", "top_k = 0\n", @@ -89,7 +75,6 @@ "voicecraft_name=\"giga330M.pth\" # or gigaHalfLibri330M_TTSEnhanced_max16s.pth, giga830M.pth\n", "\n", "# the new way of loading the model, with huggingface, recommended\n", - "from models import voicecraft\n", "model = voicecraft.VoiceCraft.from_pretrained(f\"pyp1/VoiceCraft_{voicecraft_name.replace('.pth', '')}\")\n", "phn2num = model.args.phn2num\n", "config = vars(model.args)\n", @@ -139,302 +124,74 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "cell_type": "code", - "execution_count": 5, - "metadata": { - "id": "SiWiiUpv5iQg" - }, - "outputs": [], - "source": [ - "# import libs\n", - "import torch\n", - "import torchaudio\n", - "import os\n", - "import numpy as np\n", - "import random\n", - "os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\"\n", - "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"0\"\n", - "os.environ[\"USER\"] = \"YOUR_USERNAME\" # TODO change this to your username\n", - "\n", - "from data.tokenizer import (\n", - " AudioTokenizer,\n", - " TextTokenizer,\n", - ")\n", - "\n", - "from models import voicecraft\n", - "from edit_utils import parse_edit, get_edits" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": { - "id": "a0pIv_pA5k0C" - }, - "outputs": [], - "source": [ - "# hyperparameters for inference\n", - "left_margin = 0.08\n", - "right_margin = 0.08\n", - "sub_amount = 0.01\n", - "codec_audio_sr = 16000\n", - "codec_sr = 50\n", - "top_k = 0\n", - "top_p = 0.8\n", - "temperature = 1\n", - "kvcache = 0\n", - "# NOTE: adjust the below three arguments if the generation is not as good\n", - "seed = 1 # random seed magic\n", - "silence_tokens = [1388,1898,131]\n", - "stop_repetition = -1 # if there are long silence in the generated audio, reduce the stop_repetition to 3, 2 or even 1\n", - "# what this will do to the model is that the model will run sample_batch_size examples of the same audio, and pick the one that's the shortest\n", - "def seed_everything(seed):\n", - " os.environ['PYTHONHASHSEED'] = str(seed)\n", - " random.seed(seed)\n", - " np.random.seed(seed)\n", - " torch.manual_seed(seed)\n", - " torch.cuda.manual_seed(seed)\n", - " torch.backends.cudnn.benchmark = False\n", - " torch.backends.cudnn.deterministic = True\n", - "seed_everything(seed)\n", - "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", - "\n", - "# point to the original file or record the file\n", - "# write down the transcript for the file, or run whisper to get the transcript (and you can modify it if it's not accurate), save it as a .txt file\n", - "orig_audio = \"./demo/84_121550_000074_000000.wav\"\n", - "orig_transcript = \"But when I had approached so near to them The common object, which the sense deceives, Lost not by distance any of its marks,\"\n", - "# move the audio and transcript to temp folder\n", - "temp_folder = \"./demo/temp\"\n", - "os.makedirs(temp_folder, exist_ok=True)\n", - "os.system(f\"cp {orig_audio} {temp_folder}\")\n", - "filename = os.path.splitext(orig_audio.split(\"/\")[-1])[0]\n", - "with open(f\"{temp_folder}/{filename}.txt\", \"w\") as f:\n", - " f.write(orig_transcript)\n", - "# run MFA to get the alignment\n", - "align_temp = f\"{temp_folder}/mfa_alignments\"\n", - "os.makedirs(align_temp, exist_ok=True)\n", - "os.system(f\"mfa align -j 1 --clean --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp}\")\n", - "# if it fail, it could be because the audio is too hard for the alignment model, increasing the beam size usually solves the issue\n", - "# os.system(f\"mfa align -j 1 --clean --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp} --beam 1000 --retry_beam 2000\")\n", - "audio_fn = f\"{temp_folder}/{filename}.wav\"\n", - "transcript_fn = f\"{temp_folder}/{filename}.txt\"\n", - "align_fn = f\"{align_temp}/{filename}.csv\"" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": { - "id": "iIPNTtibF4OL" - }, - "outputs": [], - "source": [ - "def get_mask_interval(ali_fn, word_span_ind, editType):\n", - " with open(ali_fn, \"r\") as rf:\n", - " data = [l.strip().split(\",\") for l in rf.readlines()]\n", - " data = data[1:]\n", - " tmp = word_span_ind.split(\",\")\n", - " s, e = int(tmp[0]), int(tmp[-1])\n", - " start = None\n", - " for j, item in enumerate(data):\n", - " if j == s and item[3] == \"words\":\n", - " if editType == 'insertion':\n", - " start = float(item[1])\n", - " else:\n", - " start = float(item[0])\n", - " if j == e and item[3] == \"words\":\n", - " if editType == 'insertion':\n", - " end = float(item[0])\n", - " else:\n", - " end = float(item[1])\n", - " assert start != None\n", - " break\n", - " return (start, end)\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 280 - }, - "id": "krbq1mBM6GDE", - "outputId": "d9267aef-05b2-4276-ee8b-5687cab5c612" - }, - "outputs": [], - "source": [ - "# propose what do you want the target modified transcript to be\n", - "orig_transcript = \"But when I had approached so near to them which the sense deceives, Lost not by distance any of its marks,\"\n", - "target_transcript = \"But I did approached so near to them which the sense deceives, Lost not by distance any of its marks,\"\n", - "\n", - "# from edit_utils import parse_edit, get_edits\n", - "\n", - "# run the script to turn user input to the format that the model can take\n", - "operations, orig_span, new_span = parse_edit(orig_transcript, target_transcript)\n", - "\n", - "used_edits = get_edits(operations)\n", - "print(used_edits) \n", - "\n", - "def process_span(span):\n", - " if span[0] > span[1]:\n", - " raise RuntimeError(f\"example {audio_fn} failed\")\n", - " if span[0] == span[1]:\n", - " return [span[0]]\n", - " return span\n", - "\n", - "print(\"orig_span: \", orig_span)\n", - "print(\"new_span: \", new_span)\n", - "orig_span_save = [process_span(span) for span in orig_span]\n", - "new_span_save = [process_span(span) for span in new_span]\n", - "\n", - "orig_span_saves = [\",\".join([str(item) for item in span]) for span in orig_span_save]\n", - "new_span_saves = [\",\".join([str(item) for item in span]) for span in new_span_save]\n", - "\n", - "starting_intervals = []\n", - "ending_intervals = []\n", - "for i, orig_span_save in enumerate(orig_span_saves):\n", - " start, end = get_mask_interval(align_fn, orig_span_save, used_edits[i])\n", - " starting_intervals.append(start)\n", - " ending_intervals.append(end)\n", - "\n", - "info = torchaudio.info(audio_fn)\n", - "audio_dur = info.num_frames / info.sample_rate\n", - "\n", - "def resolve_overlap(starting_intervals, ending_intervals, audio_dur, codec_sr, left_margin, right_margin, sub_amount):\n", - " while True:\n", - " morphed_span = [(max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur))\n", - " for start, end in zip(starting_intervals, ending_intervals)] # in seconds\n", - " mask_interval = [[round(span[0]*codec_sr), round(span[1]*codec_sr)] for span in morphed_span]\n", - " # Check for overlap\n", - " overlapping = any(a[1] >= b[0] for a, b in zip(mask_interval, mask_interval[1:]))\n", - " if not overlapping:\n", - " break\n", - " \n", - " # Reduce margins\n", - " left_margin -= sub_amount\n", - " right_margin -= sub_amount\n", - " \n", - " return mask_interval\n", - "\n", - "\n", - "# span in codec frames\n", - "mask_interval = resolve_overlap(starting_intervals, ending_intervals, audio_dur, codec_sr, left_margin, right_margin, sub_amount)\n", - "mask_interval = torch.LongTensor(mask_interval) # [M,2], M==1 for now\n", - "\n", - "# load model, tokenizer, and other necessary files\n", - "voicecraft_name=\"giga330M.pth\" # or giga830M.pth, or the newer models at https://huggingface.co/pyp1/VoiceCraft/tree/main\n", - "ckpt_fn =f\"./pretrained_models/{voicecraft_name}\"\n", - "encodec_fn = \"./pretrained_models/encodec_4cb2048_giga.th\"\n", - "if not os.path.exists(ckpt_fn):\n", - " os.system(f\"wget https://huggingface.co/pyp1/VoiceCraft/resolve/main/{voicecraft_name}\\?download\\=true\")\n", - " os.system(f\"mv {voicecraft_name}\\?download\\=true ./pretrained_models/{voicecraft_name}\")\n", - "if not os.path.exists(encodec_fn):\n", - " os.system(f\"wget https://huggingface.co/pyp1/VoiceCraft/resolve/main/encodec_4cb2048_giga.th\")\n", - " os.system(f\"mv encodec_4cb2048_giga.th ./pretrained_models/encodec_4cb2048_giga.th\")\n", - "ckpt = torch.load(ckpt_fn, map_location=\"cpu\")\n", - "model = voicecraft.VoiceCraft(ckpt[\"config\"])\n", - "model.load_state_dict(ckpt[\"model\"])\n", - "model.to(device)\n", - "model.eval()\n", - "\n", - "phn2num = ckpt['phn2num']\n", - "\n", - "text_tokenizer = TextTokenizer(backend=\"espeak\")\n", - "audio_tokenizer = AudioTokenizer(signature=encodec_fn) # will also put the neural codec model on gpu\n", - "\n", - "# run the model to get the output\n", - "from inference_speech_editing_scale import inference_one_sample\n", - "\n", - "decode_config = {'top_k': top_k, 'top_p': top_p, 'temperature': temperature, 'stop_repetition': stop_repetition, 'kvcache': kvcache, \"codec_audio_sr\": codec_audio_sr, \"codec_sr\": codec_sr, \"silence_tokens\": silence_tokens}\n", - "orig_audio, new_audio = inference_one_sample(model, ckpt[\"config\"], phn2num, text_tokenizer, audio_tokenizer, audio_fn, target_transcript, mask_interval, device, decode_config)\n", - "\n", - "# save segments for comparison\n", - "orig_audio, new_audio = orig_audio[0].cpu(), new_audio[0].cpu()\n", - "# logging.info(f\"length of the resynthesize orig audio: {orig_audio.shape}\")\n", - "\n", - "# display the audio\n", - "from IPython.display import Audio\n", - "print(\"original:\")\n", - "display(Audio(orig_audio, rate=codec_audio_sr))\n", - "\n", - "print(\"edited:\")\n", - "display(Audio(new_audio, rate=codec_audio_sr))\n", - "\n", - "# # save the audio\n", - "# # output_dir\n", - "# output_dir = \"./demo/generated_se\"\n", - "# os.makedirs(output_dir, exist_ok=True)\n", - "\n", - "# save_fn_new = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_new_seed{seed}.wav\"\n", - "\n", - "# torchaudio.save(save_fn_new, new_audio, codec_audio_sr)\n", - "\n", - "# save_fn_orig = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_orig.wav\"\n", - "# if not os.path.isfile(save_fn_orig):\n", - "# orig_audio, orig_sr = torchaudio.load(audio_fn)\n", - "# if orig_sr != codec_audio_sr:\n", - "# orig_audio = torchaudio.transforms.Resample(orig_sr, codec_audio_sr)(orig_audio)\n", - "# torchaudio.save(save_fn_orig, orig_audio, codec_audio_sr)\n", - "\n", - "# # if you get error importing T5 in transformers\n", - "# # try\n", - "# # pip uninstall Pillow\n", - "# # pip install Pillow\n", - "# # you are likely to get warning looks like WARNING:phonemizer:words count mismatch on 300.0% of the lines (3/1), this can be safely ignored" - ] - } - ], + "outputs": [], "source": [ - "editTypes_set = set(['substitution', 'insertion', 'deletion'])\n", "# propose what do you want the target modified transcript to be\n", - "target_transcript = \"But when I saw the mirage of the lake in the distance, which the sense deceives, Lost not by distance any of its marks,\"\n", - "edit_type = \"substitution\"\n", - "assert edit_type in editTypes_set, f\"Invalid edit type {edit_type}. Must be one of {editTypes_set}.\"\n", - "\n", - "# if you want to do a second modification on top of the first one, write down the second modification (target_transcript2, type_of_modification2)\n", - "# make sure the two modification do not overlap, if they do, you need to combine them into one modification\n", + "target_transcript = \"But when I had approached so near, that the sense deceives, Lost not by farness any of its marks trying insertion,\"\n", + "print(\"orig: \", orig_transcript)\n", + "print(\"trgt: \", target_transcript)\n", "\n", "# run the script to turn user input to the format that the model can take\n", - "from edit_utils import get_span\n", - "orig_span, new_span = get_span(orig_transcript, target_transcript, edit_type)\n", - "if orig_span[0] > orig_span[1]:\n", - " RuntimeError(f\"example {audio_fn} failed\")\n", - "if orig_span[0] == orig_span[1]:\n", - " orig_span_save = [orig_span[0]]\n", - "else:\n", - " orig_span_save = orig_span\n", - "if new_span[0] == new_span[1]:\n", - " new_span_save = [new_span[0]]\n", - "else:\n", - " new_span_save = new_span\n", + "operations, orig_span, new_span = parse_edit(orig_transcript, target_transcript)\n", + "if operations[-1] == 'i':\n", + " raise RuntimeError(\"The last operation should not be insertion. Please use text to speech instead\")\n", + "print(operations)\n", + "used_edits = get_edits(operations)\n", + "print(used_edits)\n", + "\n", + "def process_span(span):\n", + " if span[0] > span[1]:\n", + " raise RuntimeError(f\"example {audio_fn} failed\")\n", + " if span[0] == span[1]:\n", + " return [span[0]]\n", + " return span\n", + "\n", + "print(\"orig_span: \", orig_span)\n", + "print(\"new_span: \", new_span)\n", + "orig_span_save = [process_span(span) for span in orig_span]\n", + "new_span_save = [process_span(span) for span in new_span]\n", + "\n", + "orig_span_saves = [\",\".join([str(item) for item in span]) for span in orig_span_save]\n", + "new_span_saves = [\",\".join([str(item) for item in span]) for span in new_span_save]\n", + "\n", + "starting_intervals = []\n", + "ending_intervals = []\n", + "for i, orig_span_save in enumerate(orig_span_saves):\n", + " start, end = get_mask_interval(align_fn, orig_span_save, used_edits[i])\n", + " starting_intervals.append(start)\n", + " ending_intervals.append(end)\n", + "\n", + "print(\"intervals: \", starting_intervals, ending_intervals)\n", "\n", - "orig_span_save = \",\".join([str(item) for item in orig_span_save])\n", - "new_span_save = \",\".join([str(item) for item in new_span_save])\n", - "from inference_speech_editing_scale import get_mask_interval\n", - "\n", - "start, end = get_mask_interval(align_fn, orig_span_save, edit_type)\n", "info = torchaudio.info(audio_fn)\n", "audio_dur = info.num_frames / info.sample_rate\n", - "morphed_span = (max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur)) # in seconds\n", - "\n", - "# span in codec frames\n", - "mask_interval = [[round(morphed_span[0]*codec_sr), round(morphed_span[1]*codec_sr)]]\n", - "mask_interval = torch.LongTensor(mask_interval) # [M,2], M==1 for now\n", "\n", + "def resolve_overlap(starting_intervals, ending_intervals, audio_dur, codec_sr, left_margin, right_margin, sub_amount):\n", + " while True:\n", + " morphed_span = [(max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur))\n", + " for start, end in zip(starting_intervals, ending_intervals)] # in seconds\n", + " mask_interval = [[round(span[0]*codec_sr), round(span[1]*codec_sr)] for span in morphed_span]\n", + " # Check for overlap\n", + " overlapping = any(a[1] >= b[0] for a, b in zip(mask_interval, mask_interval[1:]))\n", + " if not overlapping:\n", + " break\n", + " \n", + " # Reduce margins\n", + " left_margin -= sub_amount\n", + " right_margin -= sub_amount\n", + " \n", + " return mask_interval\n", "\n", "\n", + "# span in codec frames\n", + "mask_interval = resolve_overlap(starting_intervals, ending_intervals, audio_dur, codec_sr, left_margin, right_margin, sub_amount)\n", + "mask_interval = torch.LongTensor(mask_interval) # [M,2], M==1 for now\n", "# run the model to get the output\n", - "from inference_speech_editing_scale import inference_one_sample\n", - "\n", "decode_config = {'top_k': top_k, 'top_p': top_p, 'temperature': temperature, 'stop_repetition': stop_repetition, 'kvcache': kvcache, \"codec_audio_sr\": codec_audio_sr, \"codec_sr\": codec_sr, \"silence_tokens\": silence_tokens}\n", "orig_audio, new_audio = inference_one_sample(model, Namespace(**config), phn2num, text_tokenizer, audio_tokenizer, audio_fn, target_transcript, mask_interval, device, decode_config)\n", - " \n", + "\n", "# save segments for comparison\n", "orig_audio, new_audio = orig_audio[0].cpu(), new_audio[0].cpu()\n", "# logging.info(f\"length of the resynthesize orig audio: {orig_audio.shape}\")\n", @@ -464,18 +221,11 @@ "# torchaudio.save(save_fn_orig, orig_audio, codec_audio_sr)\n", "\n", "# # if you get error importing T5 in transformers\n", - "# # try \n", + "# # try\n", "# # pip uninstall Pillow\n", "# # pip install Pillow\n", "# # you are likely to get warning looks like WARNING:phonemizer:words count mismatch on 300.0% of the lines (3/1), this can be safely ignored" ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] } ], "metadata": { @@ -484,7 +234,21 @@ "language": "python", "name": "python3" }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.9.16" + }, "nbformat": 4, "nbformat_minor": 0 + }, + "nbformat": 4, + "nbformat_minor": 2 } -} \ No newline at end of file From 0bf07d2214f33eb6a24ebd1ecd83e828047ac443 Mon Sep 17 00:00:00 2001 From: Pranay Gosar Date: Sun, 5 May 2024 17:24:48 -0500 Subject: [PATCH 7/8] remove ending insertion --- inference_speech_editing.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/inference_speech_editing.ipynb b/inference_speech_editing.ipynb index 0abcb59..852d4f0 100644 --- a/inference_speech_editing.ipynb +++ b/inference_speech_editing.ipynb @@ -129,7 +129,7 @@ "outputs": [], "source": [ "# propose what do you want the target modified transcript to be\n", - "target_transcript = \"But when I had approached so near, that the sense deceives, Lost not by farness any of its marks trying insertion,\"\n", + "target_transcript = \"But when I had approached so near, that the sense deceives, Lost not by farness any of its marks,\"\n", "print(\"orig: \", orig_transcript)\n", "print(\"trgt: \", target_transcript)\n", "\n", From 503f3ffd6eac83f9e2bc2f02e2a933d005a0f055 Mon Sep 17 00:00:00 2001 From: pgosar Date: Tue, 7 May 2024 17:58:56 -0500 Subject: [PATCH 8/8] fix regex for contractions --- edit_utils.py | 32 ++++++++++++++++++++------------ 1 file changed, 20 insertions(+), 12 deletions(-) diff --git a/edit_utils.py b/edit_utils.py index 3a6883d..990de64 100644 --- a/edit_utils.py +++ b/edit_utils.py @@ -37,42 +37,48 @@ def levenshtein_distance(word1, word2): def extract_words(sentence): - words = re.findall(r"\b\w+\b", sentence) + words = re.findall(r"\b[\w']+\b", sentence) return words + # edge cases for spans of deletion, insertion, substitution def handle_delete(start, end, orig, new): orig.append([start, end - 1]) new.append([start - 1, start]) + def handle_insert(start, end, orig, new): temp_new = [start - 1, start] orig.append(temp_new) new.append(orig[-1]) orig[-1], new[-1] = new[-1], temp_new + def handle_substitute(start, end, orig, new): orig.append([start, end - 1]) new.append([start, end - 1]) + # editing the last index of the sentence is another edge case def handle_last_operation(prev_op, start, end, orig, new): - if prev_op == 'd': + if prev_op == "d": handle_delete(start, end, orig, new) - elif prev_op == 'i': + elif prev_op == "i": handle_insert(start, end, orig, new) - elif prev_op == 's': + elif prev_op == "s": handle_substitute(start, end, orig, new) + # adjust spans according to edge case expected output def adjust_last_span(operations, orig, new): - if operations[-1] == 'd': + if operations[-1] == "d": new[-1] = [new[-1][0] - 1, new[-1][1] - 1] orig[-1] = [orig[-1][0] - 1, orig[-1][0] - 1] - elif operations[-1] == 'i': + elif operations[-1] == "i": new[-1] = [new[-1][0] - 1, new[-1][1] - 1] orig[-1] = [orig[-1][0] - 1, orig[-1][0]] + def get_spans(operations): orig = [] new = [] @@ -81,7 +87,7 @@ def get_spans(operations): end = 0 for i, op in enumerate(operations): # prevent span duplication of sequential edits of the same type - if op != '=': + if op != "=": if op != prev_op: if prev_op: handle_last_operation(prev_op, start, end, orig, new) @@ -99,22 +105,24 @@ def get_spans(operations): adjust_last_span(operations, orig, new) return orig, new + def get_edits(operations): used_edits = [] - prev_op = '' + prev_op = "" for op in operations: - if op == 'i' and prev_op != 'i': + if op == "i" and prev_op != "i": used_edits.append("insertion") - elif op == 'd' and prev_op != 'd': + elif op == "d" and prev_op != "d": used_edits.append("deletion") - elif op == 's' and prev_op != 's': + elif op == "s" and prev_op != "s": used_edits.append("substitution") prev_op = op return used_edits + def parse_edit(orig_transcript, trgt_transcript): word1 = extract_words(orig_transcript) word2 = extract_words(trgt_transcript) distance, operations = levenshtein_distance(word1, word2) orig_span, new_span = get_spans(operations) - return operations, orig_span, new_span \ No newline at end of file + return operations, orig_span, new_span