speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

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

Browse Source 
update infer_online.py
This commit is contained in:
zhifu gao 2023-03-14 14:43:32 +08:00 committed by GitHub
commit 681868deae
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer.py
View File

@ -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,
)

5
egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer_online.py
View File

@ -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]

4
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py
View File

@ -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)

5
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py
View File

@ -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]