Merge pull request #146 from chigkim/multivoice

Multivoice CLI Similar to Gradio App

inference-cli.py

@@ -282,29 +282,12 @@ def infer_batch(ref_audio, ref_text, gen_text_batches, model, remove_silence, cr
 
             final_wave = new_wave
 
-    with open(wave_path, "wb") as f:
-        sf.write(f.name, final_wave, target_sample_rate)
-        # Remove silence
-        if remove_silence:
-            aseg = AudioSegment.from_file(f.name)
-            non_silent_segs = silence.split_on_silence(aseg, min_silence_len=1000, silence_thresh=-50, keep_silence=500)
-            non_silent_wave = AudioSegment.silent(duration=0)
-            for non_silent_seg in non_silent_segs:
-                non_silent_wave += non_silent_seg
-            aseg = non_silent_wave
-            aseg.export(f.name, format="wav")
-        print(f.name)
-
     # Create a combined spectrogram
     combined_spectrogram = np.concatenate(spectrograms, axis=1)
-    save_spectrogram(combined_spectrogram, spectrogram_path)
-    print(spectrogram_path)
-
 
-def infer(ref_audio_orig, ref_text, gen_text, model, remove_silence, cross_fade_duration=0.15):
-
-    print(gen_text)
+    return final_wave, combined_spectrogram
 
+def process_voice(ref_audio_orig, ref_text):
     print("Converting audio...")
     with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as f:
         aseg = AudioSegment.from_file(ref_audio_orig)
@@ -340,7 +323,10 @@ def infer(ref_audio_orig, ref_text, gen_text, model, remove_silence, cross_fade_
         print("Finished transcription")
     else:
         print("Using custom reference text...")
+    return ref_audio, ref_text    
 
+def infer(ref_audio, ref_text, gen_text, model, remove_silence, cross_fade_duration=0.15):
+    print(gen_text)
     # Add the functionality to ensure it ends with ". "
     if not ref_text.endswith(". ") and not ref_text.endswith("。"):
         if ref_text.endswith("."):
@@ -360,4 +346,47 @@ def infer(ref_audio_orig, ref_text, gen_text, model, remove_silence, cross_fade_
     return infer_batch((audio, sr), ref_text, gen_text_batches, model, remove_silence, cross_fade_duration)
 
 
-infer(ref_audio, ref_text, gen_text, model, remove_silence)
+def process(ref_audio, ref_text, text_gen, model, remove_silence):
+    main_voice = {"ref_audio":ref_audio, "ref_text":ref_text}
+    if "voices" not in config:
+        voices = {"main": main_voice}
+    else:
+        voices = config["voices"]
+        voices["main"] = main_voice
+    for voice in voices:
+        voices[voice]['ref_audio'], voices[voice]['ref_text'] = process_voice(voices[voice]['ref_audio'], voices[voice]['ref_text'])
+
+    generated_audio_segments = []
+    reg1 = r'(?=\[\w+\])'
+    chunks = re.split(reg1, text_gen)
+    reg2 = r'\[(\w+)\]'
+    for text in chunks:
+        match = re.match(reg2, text)
+        if not match or voice not in voices:
+            voice = "main"
+        else:
+            voice = match[1]
+        text = re.sub(reg2, "", text)
+        gen_text = text.strip()
+        ref_audio = voices[voice]['ref_audio']
+        ref_text = voices[voice]['ref_text']
+        print(f"Voice: {voice}")
+        audio, spectragram = infer(ref_audio, ref_text, gen_text, model, remove_silence)
+        generated_audio_segments.append(audio)
+
+    if generated_audio_segments:
+        final_wave = np.concatenate(generated_audio_segments)
+        with open(wave_path, "wb") as f:
+            sf.write(f.name, final_wave, target_sample_rate)
+            # Remove silence
+            if remove_silence:
+                aseg = AudioSegment.from_file(f.name)
+                non_silent_segs = silence.split_on_silence(aseg, min_silence_len=1000, silence_thresh=-50, keep_silence=500)
+                non_silent_wave = AudioSegment.silent(duration=0)
+                for non_silent_seg in non_silent_segs:
+                    non_silent_wave += non_silent_seg
+                aseg = non_silent_wave
+                aseg.export(f.name, format="wav")
+            print(f.name)
+
+process(ref_audio, ref_text, gen_text, model, remove_silence)

samples/story.toml

@@ -0,0 +1,19 @@
+# F5-TTS | E2-TTS
+model = "F5-TTS"
+ref_audio = "samples/main.flac"
+# If an empty "", transcribes the reference audio automatically.
+ref_text = ""
+gen_text = ""
+# File with text to generate. Ignores the text above.
+gen_file = "samples/story.txt"
+remove_silence = true
+output_dir = "samples"
+
+[voices.town]
+ref_audio = "samples/town.flac"
+ref_text = ""
+
+[voices.country]
+ref_audio = "samples/country.flac"
+ref_text = ""
+

samples/story.txt

@@ -0,0 +1 @@
+A Town Mouse and a Country Mouse were acquaintances, and the Country Mouse one day invited his friend to come and see him at his home in the fields. The Town Mouse came, and they sat down to a dinner of barleycorns and roots, the latter of which had a distinctly earthy flavour. The fare was not much to the taste of the guest, and presently he broke out with [town] “My poor dear friend, you live here no better than the ants. Now, you should just see how I fare! My larder is a regular horn of plenty. You must come and stay with me, and I promise you you shall live on the fat of the land.” [main] So when he returned to town he took the Country Mouse with him, and showed him into a larder containing flour and oatmeal and figs and honey and dates. The Country Mouse had never seen anything like it, and sat down to enjoy the luxuries his friend provided: but before they had well begun, the door of the larder opened and someone came in. The two Mice scampered off and hid themselves in a narrow and exceedingly uncomfortable hole. Presently, when all was quiet, they ventured out again; but someone else came in, and off they scuttled again. This was too much for the visitor. [country] “Goodbye,” [main] said he, [country] “I’m off. You live in the lap of luxury, I can see, but you are surrounded by dangers; whereas at home I can enjoy my simple dinner of roots and corn in peace.”