Merge pull request #225 from alibaba-damo-academy/dev_zly

update infer_online.py

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

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

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

@@ -8,9 +8,10 @@ if __name__ == '__main__':
     inference_pipline = pipeline(
         task=Tasks.voice_activity_detection,
         model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
-        model_revision='v1.1.9',
-        output_dir=None,
+        model_revision='v1.2.0',
+        output_dir=output_dir,
         batch_size=1,
+        mode='online',
     )
     speech, sample_rate = soundfile.read("./vad_example_16k.wav")
     speech_length = speech.shape[0]

egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py

@@ -7,8 +7,8 @@ if __name__ == '__main__':
     inference_pipline = pipeline(
         task=Tasks.voice_activity_detection,
         model="damo/speech_fsmn_vad_zh-cn-8k-common",
-        model_revision=None,
-        output_dir='./output_dir',
+        model_revision='v1.2.0',
+        output_dir=output_dir,
         batch_size=1,
     )
     segments_result = inference_pipline(audio_in=audio_in)

egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py

@@ -8,9 +8,10 @@ if __name__ == '__main__':
     inference_pipline = pipeline(
         task=Tasks.voice_activity_detection,
         model="damo/speech_fsmn_vad_zh-cn-8k-common",
-        model_revision='v1.1.9',
-        output_dir='./output_dir',
+        model_revision='v1.2.0',
+        output_dir=output_dir,
         batch_size=1,
+        mode='online',
     )
     speech, sample_rate = soundfile.read("./vad_example_8k.wav")
     speech_length = speech.shape[0]