Update app.py

app.py

@@ -173,7 +173,7 @@ def run(seed, sub_amount, codec_audio_sr, codec_sr, top_k, top_p, temperature,
     target_transcript = replace_numbers_with_words(transcript).replace("  ", " ").replace("  ", " ").replace("\n", " ")
     orig_transcript = replace_numbers_with_words(original_transcript).replace("  ", " ").replace("  ", " ").replace("\n", " ")
 
-    [orig_transcript, segments, _] = transcribe(audio_path)
+    [orig_transcript, segments, _, _] = transcribe(audio_path)
     orig_transcript = orig_transcript.lower()
     target_transcript = target_transcript.lower()
     transcribe_state,_ = align(segments, audio_path)
@@ -195,7 +195,7 @@ def run(seed, sub_amount, codec_audio_sr, codec_sr, top_k, top_p, temperature,
 
         audio, _ = librosa.load(audio_path, sr=16000, duration=cut_length)
         sf.write(audio_path, audio, 16000)
-        [orig_transcript, segments, _] = transcribe(audio_path)
+        [orig_transcript, segments, _, _] = transcribe(audio_path)
         
         
         orig_transcript = orig_transcript.lower()
@@ -275,7 +275,7 @@ def run(seed, sub_amount, codec_audio_sr, codec_sr, top_k, top_p, temperature,
     new_audio = new_audio[0].cpu()
     torchaudio.save(audio_path, new_audio, codec_audio_sr)
     if tts: # remove the start parts
-        [new_transcript, new_segments, _] = transcribe(audio_path)
+        [new_transcript, new_segments, _, _] = transcribe(audio_path)
         transcribe_state,_ = align(new_segments, audio_path)
         tmp1 = transcribe_state['segments'][0]['words'][0]['word'].lower()
         tmp2 = target_transcript_copy.lower()
@@ -292,17 +292,18 @@ def run(seed, sub_amount, codec_audio_sr, codec_sr, top_k, top_p, temperature,
     return output_audio, success_message
 
 
-demo_original_transcript = "Gwynplaine had, besides, for his work and for his feats of strength, round his neck and over his shoulders, an esclavine of leather."
+demo_original_transcript = "Gwynplain had besides for his work and for his feats of strength, round his neck and over his shoulders, an esclavine of leather."
 
 demo_text = {
     "TTS": {
-        "regular": "Gwynplaine had, besides, for his work and for his feats of strength, I cannot believe that the same model can also do text to speech synthesis too!"
+        "regular": "Gwynplain had besides for his work and for his feats of strength, I cannot believe that the same model can also do text to speech synthesis too!"
     },
     "Edit": {
-        "regular": "Gwynplaine had, besides, for his work and for his feats of strength, take over the stage for half an hour, an esclavine of leather."
+        "regular": "Gwynplain had besides for his work and feats of strength, hanging from his neck and shoulders, an esclavine of leather."
     },
 }
 
+
 def get_app():
     with gr.Blocks() as app:
         gr.Markdown("""