Update functions.py

functions.py

@@ -196,11 +196,12 @@ def inference(link, upload, _asr_model):
             
             audio_file, title = get_yt_audio(link)
 
-            if 'audio' not in st.session_state:
-                st.session_state['audio'] = audio_file
+            print(f'audio_file:{audio_file}')
+
+            st.session_state['audio'] = audio_file
     
             #Get size of audio file
-            audio_size = round(os.path.getsize(audio_file)/(1024*1024),1)
+            audio_size = round(os.path.getsize(st.session_state['audio'])/(1024*1024),1)
     
             #Check if file is > 24mb, if not then use Whisper API
             if audio_size <= 25:
@@ -208,13 +209,13 @@ def inference(link, upload, _asr_model):
                 st.info("`Transcribing YT audio...`")
                 
                 #Use whisper API
-                results = load_whisper_api(audio_file)['text']
+                results = load_whisper_api(st.session_state['audio'])['text']
     
             else:
     
                 st.warning('File size larger than 24mb, applying chunking and transcription',icon="⚠️")
     
-                song = AudioSegment.from_file(audio_file, format='mp4')
+                song = AudioSegment.from_file(st.session_state['audio'], format='mp4')
     
                 # PyDub handles time in milliseconds
                 twenty_minutes = 20 * 60 * 1000