Multimodal_Demo

Runtime error

Sirus1 commited on Oct 29, 2023

Commit

5f1678c

1 Parent(s): 8913584

Update models/whisper_model.py

Files changed (1) hide show

models/whisper_model.py CHANGED Viewed

@@ -14,7 +14,7 @@ class AudioTranslator():
     def __call__(self, video_path):
         print("Extract the audio results.")
-        audio_results = self.model.transcribe(video_path)["segments"]
         print("Finished.")
         return audio_results

     def __call__(self, video_path):
         print("Extract the audio results.")
+        audio_results = self.model.transcribe(video_path,language="zh")["segments"]
         print("Finished.")
         return audio_results