Application isn't loading

[Forkei]

Hi, I tried using this tool and it worked just fine. Then I tried to train a model, deleted the folder in voices and training. And when I relaunch the app, the gradio app keeps saying "Loading..." without any errors in cmd.

This is what the console says:

[2024-09-21 14:00:14,072] torch.distributed.elastic.multiprocessing.redirects: [WARNING] NOTE: Redirects are currently not supported in Windows or MacOs.
2024-09-21 14:00:14 | INFO | rvc.configs.config | Found GPU NVIDIA GeForce RTX 4070 Laptop GPU
Whisper detected
C:\Users\XX\Desktop\ai-voice-cloning-3.0\ai-voice-cloning-3.0\runtime\Lib\site-packages\gradio\components\dropdown.py:179: UserWarning: The value passed into gr.Dropdown() is not in the list of choices. Please update the list of choices to include:  or set allow_custom_value=True.
  warnings.warn(
C:\Users\XX\Desktop\ai-voice-cloning-3.0\ai-voice-cloning-3.0\runtime\Lib\site-packages\gradio\utils.py:858: UserWarning: Expected 1 arguments for function <function update_voices at 0x000002B0E3CEFEC0>, received 0.
  warnings.warn(
C:\Users\XX\Desktop\ai-voice-cloning-3.0\ai-voice-cloning-3.0\runtime\Lib\site-packages\gradio\utils.py:862: UserWarning: Expected at least 1 arguments for function <function update_voices at 0x000002B0E3CEFEC0>, received 0.
  warnings.warn(
Running on local URL:  http://127.0.0.1:7860
2024-09-21 14:00:15 | INFO | httpx | HTTP Request: GET http://127.0.0.1:7860/startup-events "HTTP/1.1 200 OK"
2024-09-21 14:00:15 | INFO | httpx | HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK"

To create a public link, set `share=True` in `launch()`.
Loading TorToiSe... (AR: None, diffusion: None, vocoder: bigvgan_24khz_100band)
Hardware acceleration found: cuda
use_deepspeed api_debug False
2024-09-21 14:00:15 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
IMPORTANT: You are using gradio version 4.22.0, however version 4.29.0 is available, please upgrade.
--------
C:\Users\XX\Desktop\ai-voice-cloning-3.0\ai-voice-cloning-3.0\runtime\Lib\site-packages\torch\nn\utils\weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
  warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
Loading tokenizer JSON: C:\Users\forke\Desktop\CS\ai-voice-cloning-3.0\ai-voice-cloning-3.0\src\tortoise\../tortoise/data/tokenizer.json
Loaded tokenizer
Loading autoregressive model: C:\Users\XX\Desktop\ai-voice-cloning-3.0\ai-voice-cloning-3.0\models\tortoise\autoregressive.pth
Loaded autoregressive model
Loaded diffusion model
Loading vocoder model: bigvgan_24khz_100band
Loading vocoder model: bigvgan_24khz_100band.pth
Removing weight norm...
Loaded vocoder model
Loaded TTS, ready for generation.```

I have tried reinstalling the whole ai-voice-cloning folder and even reinstalling gradio. 
If you have any idea why this is happening, thank you.

[zono50]

i'm running into the same issue. Are you using the docker?

[Forkei]

i'm running into the same issue. Are you using the docker?

No I don't believe so. Did you get the same error message?

[Juanchote]

same problem here with docker. I get a loading screen and later a few errors from the browser