Update app.py

app.py

@@ -103,7 +103,7 @@ def Transcribe_V1(NumberOfSpeakers, SpeakerNames="", audio="temp_audio.wav"):
         return f"dz_{audio}.wav", dzList, segments
     
     def transcribe(dz_audio):
-        model = whisper.load_model("large-v2")
+        model = whisper.load_model("medium")
         result = model.transcribe(dz_audio)
         # for _ in result['segments']:
         #     print(_['start'], _['end'], _['text'])
@@ -138,7 +138,7 @@ def Transcribe_V1(NumberOfSpeakers, SpeakerNames="", audio="temp_audio.wav"):
 
 
 def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
-    model = whisper.load_model("large-v2")
+    model = whisper.load_model("medium")
     embedding_model = PretrainedSpeakerEmbedding(
         "speechbrain/spkrec-ecapa-voxceleb",
         device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')