Update app.py

app.py

@@ -98,7 +98,7 @@ def predict_answer(video, image, question):
             
             answer = tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()
             answers.append(answer)
-        return answers
+        return ast.literal_eval(answers[0])
         
     else:
         return "Unsupported file type. Please upload an image or video."