Update app.py

app.py

@@ -181,14 +181,14 @@ def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
 
 	def get_duration(path):
 		with contextlib.closing(wave.open(path,'r')) as f:
-		frames = f.getnframes()
-		rate = f.getframerate()
-		return frames / float(rate)
+			frames = f.getnframes()
+			rate = f.getframerate()
+			return frames / float(rate)
 
 	def make_embeddings(path, segments, duration):
 		embeddings = np.zeros(shape=(len(segments), 192))
 		for i, segment in enumerate(segments):
-		embeddings[i] = segment_embedding(path, segment, duration)
+			embeddings[i] = segment_embedding(path, segment, duration)
 		return np.nan_to_num(embeddings)
 
 	def segment_embedding(path, segment, duration):
@@ -203,7 +203,7 @@ def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
 		clustering = AgglomerativeClustering(num_speakers).fit(embeddings)
 		labels = clustering.labels_
 		for i in range(len(segments)):
-		segments[i]["speaker"] = 'SPEAKER ' + str(labels[i] + 1)
+			segments[i]["speaker"] = 'SPEAKER ' + str(labels[i] + 1)
 
 	def time(secs):
 		return datetime.timedelta(seconds=round(secs))