Update app.py

app.py

@@ -17,7 +17,7 @@ import moviepy.editor as mp
 import datetime
 import torch
 import pyannote.audio
-from pyannote.audio.pipelines.speaker_verification import PretrainedSpeakerEmbedding
+from pyannote.audio.pipelines.speaker_verification import NeMoPretrainedSpeakerEmbedding
 from pyannote.audio import Audio
 from pyannote.core import Segment
 import wave
@@ -141,10 +141,11 @@ def Transcribe_V1(NumberOfSpeakers, SpeakerNames="", audio="temp_audio.wav"):
 
 def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
     model = whisper.load_model("medium")
-    embedding_model = PretrainedSpeakerEmbedding(
-        "speechbrain/spkrec-ecapa-voxceleb",
-        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-    )
+    embedding_model = NeMoPretrainedSpeakerEmbedding()
+    # embedding_model = PretrainedSpeakerEmbedding(
+    #     "speechbrain/spkrec-ecapa-voxceleb",
+    #     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+    # )
     SPEAKER_DICT = {}
     SPEAKERS = [speaker.strip() for speaker in speaker_names.split(',') if len(speaker)]
     def GetSpeaker(sp):