Update app.py

app.py

@@ -92,9 +92,9 @@ def predict_answer(video, image, question):
                 max_new_tokens=25,
                 images=image_tensor,
                 use_cache=True)[0]
-            
-        return tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()
-        
+        answer = tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()
+
+        return ast.literal_eval(answer)
         # # Process as a video
         # frames = video_to_frames(video)
         # answers = []