Update app.py

app.py

@@ -150,7 +150,7 @@ def Transcribe(NumberOfSpeakers, SpeakerNames="", audio="temp_audio.wav"):
 
 def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
     SPEAKER_DICT = {}
-    SPEAKERS = []
+    SPEAKERS = [speaker.strip() for speaker in sp.split(',')]
     def GetSpeaker(sp):
         speaker = sp
         if sp not in list(SPEAKER_DICT.keys()):
@@ -162,12 +162,7 @@ def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
             speaker = SPEAKER_DICT[sp]
         return speaker
     
-    def GenerateSpeakerDict(sp):
-        global SPEAKERS
-        SPEAKERS = [speaker.strip() for speaker in sp.split(',')]
-
     # audio = Audio()
-    GenerateSpeakerDict(speaker_names)
     def get_output(segments):
         # print(segments)
         conversation=[]
@@ -184,7 +179,7 @@ def Transcribe_V2(num_speakers, speaker_names, audio="temp_audio.wav"):
             #         conversation.append([GetSpeaker(segment["speaker"]), segment["text"][1:]]) # segment["speaker"] + ' ' + str(time(segment["start"])) + '\n\n'
             # conversation[-1][1] += segment["text"][1:]
         # return output
-        return conversation, ("".join([f"{speaker} --> {text}\n" for speaker, text in conversation]))
+        return ("".join([f"{speaker} --> {text}\n" for speaker, text in conversation])), conversation
 
     def get_duration(path):
         with contextlib.closing(wave.open(path,'r')) as f: