Update app.py

app.py

@@ -22,6 +22,7 @@ emotion_dict = {
     'neu': 'Neutral'
 }
 
+pipe = pipeline("automatic-speech-recognition")
 
 # Create a Gradio interface with audio file and text inputs
 def classify_toxicity(audio_file, text_input, classify_anxiety):
@@ -39,8 +40,9 @@ def classify_toxicity(audio_file, text_input, classify_anxiety):
         # Extract the transcribed text
         # transcribed_text = transcription_results["transcription"]
         '''
-        model = whisper.load_model("base")
-        transcribed_text = model.transcribe(audio_file)
+        # model = whisper.load_model("base")
+        # transcribed_text = model.transcribe(audio_file)
+        transcribed_text = pipe(audio_file)["text"]
         
         #### Emotion classification ####
         emotion_classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")