Update app.py

app.py

@@ -470,7 +470,7 @@ def run_edit_zh(seed, sub_amount, aug_text, cfg_coef, cfg_stride, prompt_length,
 
     converter = opencc.OpenCC('t2s')
     orig_transcript = converter.convert(orig_transcript)
-    transcribe_state = align_zh(traditional_to_simplified(segments), audio_path)
+    transcribe_state,_ = align_zh(traditional_to_simplified(segments), audio_path)
     transcribe_state['segments'] = traditional_to_simplified(transcribe_state['segments'])
 
     print(orig_transcript)
@@ -568,7 +568,7 @@ def run_tts_zh(seed, sub_amount, aug_text, cfg_coef, cfg_stride, prompt_length,
 
     converter = opencc.OpenCC('t2s')
     orig_transcript = converter.convert(orig_transcript)
-    transcribe_state = align_zh(traditional_to_simplified(segments), audio_path)
+    transcribe_state,_ = align_zh(traditional_to_simplified(segments), audio_path)
     transcribe_state['segments'] = traditional_to_simplified(transcribe_state['segments'])
 
     print(orig_transcript)
@@ -593,7 +593,7 @@ def run_tts_zh(seed, sub_amount, aug_text, cfg_coef, cfg_stride, prompt_length,
 
     converter = opencc.OpenCC('t2s')
     orig_transcript = converter.convert(orig_transcript)
-    transcribe_state = align_zh(traditional_to_simplified(segments), audio_path)
+    transcribe_state,_ = align_zh(traditional_to_simplified(segments), audio_path)
     transcribe_state['segments'] = traditional_to_simplified(transcribe_state['segments'])
     
     print(orig_transcript)
@@ -628,9 +628,9 @@ def run_tts_zh(seed, sub_amount, aug_text, cfg_coef, cfg_stride, prompt_length,
     new_audio = new_audio[0].cpu()
     torchaudio.save(audio_path, new_audio, codec_audio_sr)
     
-    [new_transcript, new_segments, _] = transcribe_zh(audio_path)
+    [new_transcript, new_segments, _,_] = transcribe_zh(audio_path)
     
-    transcribe_state = align_zh(traditional_to_simplified(new_segments), audio_path)
+    transcribe_state,_ = align_zh(traditional_to_simplified(new_segments), audio_path)
     transcribe_state['segments'] = traditional_to_simplified(transcribe_state['segments'])
     tmp1 = transcribe_state['segments'][0]['words'][0]['word']
     tmp2 = target_transcript_copy