Update app.py

app.py

@@ -77,17 +77,23 @@ def generate_image(api_key, text):
     else:
         return None
 
+        
 # Function to get predictions
 def get_predictions(audio_input):
     emotion_prediction = predict_emotion_from_audio(audio_input)
+    transcribed_text = transcribe(audio_input)
     image = generate_image(api_key, emotion_prediction)
-    return emotion_prediction, image
+    return emotion_prediction, transcribed_text, image
 
 # Create the Gradio interface
 interface = gr.Interface(
     fn=get_predictions,
-    inputs=gr.Audio(label="Input Audio", type="filepath"),
-    outputs=[gr.Label("Prediction"), gr.Image(type='pil')]
+    inputs=gr.Audio(label="Input Audio", type="file"),
+    outputs=[
+        gr.Label("Emotion Prediction"),
+        gr.Label("Transcribed Text"),
+        gr.Image(type='pil')
+    ]
 )
 
 interface.launch()