change readme for more detail

zhaomingwork

2023-05-15 c8fe32c5bc0d7ec434d4cbce9f38bd0e1617c93a

 egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/demo.py

@@ -7,7 +7,7 @@
    inference_pipeline = pipeline(
        task=Tasks.voice_activity_detection,
        model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
        model_revision='v1.2.0',
        model_revision=None,
        output_dir=output_dir,
        batch_size=1,
    )