Update app.py

app.py

@@ -157,6 +157,19 @@ def process_video(video_file, language_choice):
                 start, end, translated_text = segment
                 segment_path = os.path.join(output_dir, f'segment_{start}_{end}.wav')
                 model.tts_to_file(translated_text, speaker_id, segment_path, speed=speed)
+                
+                reference_speaker = reference_audio[start:end]  # This is the voice you want to clone
+                target_se, audio_name = se_extractor.get_se(reference_speaker, tone_color_converter, vad=False)
+                # Run the tone color converter
+                encode_message = "@MyShell"
+                tone_color_converter.convert(
+                    audio_src_path=segment_path,
+                    src_se=source_se,
+                    tgt_se=target_se,
+                    output_path=segment_path,
+                    message=encode_message
+                )
+                
                 segment_files.append((segment_path, start, end, translated_text))
             return segment_files
     
@@ -174,18 +187,7 @@ def process_video(video_file, language_choice):
                     batch_segment_files = list(executor.map(generate_segment_audio_batch, [batch] * len(speaker_ids), [speaker_id] * len(speaker_ids)))
                     batch_segment_files = [item for sublist in batch_segment_files for item in sublist]  # Flatten the list
     
-                for segment_file, start, end, translated_text in batch_segment_files:
-                    reference_speaker = reference_audio[start:end]  # This is the voice you want to clone
-                    target_se, audio_name = se_extractor.get_se(reference_speaker, tone_color_converter, vad=False)
-                    # Run the tone color converter
-                    encode_message = "@MyShell"
-                    tone_color_converter.convert(
-                        audio_src_path=segment_file,
-                        src_se=source_se,
-                        tgt_se=target_se,
-                        output_path=segment_file,
-                        message=encode_message
-                    )
+                for segment_file, start, end, translated_text in batch_segment_files:                    
                     segment_files.append((segment_file, start, end, translated_text))
     
             # Combine the audio segments