Update functions.py

functions.py

@@ -152,7 +152,7 @@ def load_whisper_api(audio):
 
     '''Transcribe YT audio to text using Open AI API'''
     file = open(audio, "rb")
-    transcript = openai_audio.audio.transcriptions.create(model="whisper-1", file=file)
+    transcript = openai_audio.audio.transcriptions.create(model="whisper-1", file=file,response_format="text")
 
     return transcript
 
@@ -179,7 +179,7 @@ def transcribe_yt_video(link, py_tube=True):
             st.info("`Transcribing YT audio...`")
             
             #Use whisper API
-            results = load_whisper_api(st.session_state['audio'])['text']
+            results = load_whisper_api(st.session_state['audio'])
 
         else:
 
@@ -200,7 +200,7 @@ def transcribe_yt_video(link, py_tube=True):
             
             for i, chunk in enumerate(chunks):
                 chunk.export(f'output/chunk_{i}_{video_id}.mp4', format='mp3')
-                transcriptions.append(load_whisper_api(f'output/chunk_{i}_{video_id}.mp3')['text'])
+                transcriptions.append(load_whisper_api(f'output/chunk_{i}_{video_id}.mp3'))
 
             results = ','.join(transcriptions)
 
@@ -244,7 +244,7 @@ def transcribe_yt_video(link, py_tube=True):
             
             for i, chunk in enumerate(chunks):
                 chunk.export(f'output/chunk_{i}_{video_id}.mp3', format='mp3')
-                transcriptions.append(load_whisper_api(f'output/chunk_{i}_{video_id}.mp4')['text'])
+                transcriptions.append(load_whisper_api(f'output/chunk_{i}_{video_id}.mp3')
 
             results = ','.join(transcriptions)