category was 0

app.py

@@ -253,7 +253,7 @@ def combine(audio, input_image, text_question=""):
 
     image = Image.fromarray(input_image).convert('RGB')
     category = predict_category(que, image)
-    answer = predict_answer(0, que, image)
+    answer = predict_answer(category, que, image)
 
     tts = gTTS(answer)
     tts.save('answer.mp3')