diff --git a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
index 5ebeff9ba..df471d6dc 100644
--- a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
+++ b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
@@ -7,10 +7,13 @@ if __name__ == '__main__':
     inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+        model_revision="v1.2.1",
         vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
         vad_model_revision="v1.1.8",
         punc_model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
-        punc_model_revision="v1.1.6")
+        punc_model_revision="v1.1.6",
+        ngpu=1,
+    )
     rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)