Update app.py

app.py

@@ -228,7 +228,7 @@ def transcribe_video_with_speakers(video_path):
             "start": segment["start"],
             "end": segment["end"],
             "text": segment["text"],
-            "speaker": segment["speaker"]
+            "speaker": segment.get("speaker", "SPEAKER_00")
         }
         for segment in result["segments"]
     ]
@@ -588,7 +588,7 @@ def process_entry(entry, i, tts_model, video_width, video_height, process_mode,
             desired_duration = entry["end"] - entry["start"]
             desired_speed = entry['speed'] #calibrated_speed(entry['translated'], desired_duration)
 
-            speaker = entry.get("speaker", "default")
+            speaker = entry.get("speaker", "SPEAKER_00")
             speaker_wav_path = f"speaker_{speaker}_sample.wav"
 
             if process_mode > 2 and speaker_wav_path and os.path.exists(speaker_wav_path) and target_language in tts_model.synthesizer.tts_model.language_manager.name_to_id.keys():