Update app.py

app.py

@@ -33,6 +33,8 @@ def ask_image(image, audio):
     generated_ids = model.generate(**inputs)
     answer = processor.decode(generated_ids[0], skip_special_tokens=True)
 
+    print(f"Answer: {answer}")
+    
     # Convert the answer to speech
     tts = gTTS(answer)
     with NamedTemporaryFile(delete=False, suffix=".mp3") as f: