Update app.py

app.py

@@ -140,7 +140,7 @@ def inference(wav_path, log_name: str, folder_path="./tmp"):
             input = embed_img(file_path)
             output = model(input)
             pred_id = torch.max(output.data, 1)[1]
-            outputs.append(pred_id)
+            outputs.append(int(pred_id))
 
     max_count_item = most_common_element(outputs)
     shutil.rmtree(folder_path)