Update app.py

app.py

@@ -166,7 +166,7 @@ def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
 		global SPEAKERS
 		SPEAKERS = [speaker.strip() for speaker in sp.split(',')]
 
-	audio = Audio()
+	# audio = Audio()
 	GenerateSpeakerDict(speaker_names)
 	def get_output(segments):
 		# print(segments)
@@ -183,7 +183,7 @@ def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
 		with contextlib.closing(wave.open(path,'r')) as f:
 			frames = f.getnframes()
 			rate = f.getframerate()
-			return frames / float(rate)
+		return frames / float(rate)
 
 	def make_embeddings(path, segments, duration):
 		embeddings = np.zeros(shape=(len(segments), 192))
@@ -196,7 +196,7 @@ def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
 		# Whisper overshoots the end timestamp in the last segment
 		end = min(duration, segment["end"])
 		clip = Segment(start, end)
-		waveform, sample_rate = audio.crop(path, clip)
+		waveform, sample_rate = Audio().crop(path, clip)
 		return embedding_model(waveform[None])
 
 	def add_speaker_labels(segments, embeddings, num_speakers):