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

vad docs

Browse Source
This commit is contained in:
游雁 2023-05-10 15:23:08 +08:00
parent 4d8a1c189a
commit a85cfe4a31
12 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
egs_modelscope/vad/TEMPLATE/README.md
View File

@ -83,7 +83,7 @@ FunASR also offer recipes [egs_modelscope/vad/TEMPLATE/infer.sh](https://github.
#### Decode with multi GPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
--model "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch" \
--data_dir "./data/test" \
--output_dir "./results" \
--batch_size 1 \
@ -93,7 +93,7 @@ FunASR also offer recipes [egs_modelscope/vad/TEMPLATE/infer.sh](https://github.
#### Decode with multi-thread CPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
--model "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch" \
--data_dir "./data/test" \
--output_dir "./results" \
--gpu_inference false \

4
egs_modelscope/vad/TEMPLATE/infer.py
View File

@ -16,10 +16,10 @@ def modelscope_infer(args):
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--model', type=str, default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
parser.add_argument('--model', type=str, default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch")
parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
parser.add_argument('--output_dir', type=str, default="./results/")
parser.add_argument('--batch_size', type=int, default=64)
parser.add_argument('--batch_size', type=int, default=1)
parser.add_argument('--gpuid', type=str, default="0")
args = parser.parse_args()
modelscope_infer(args)

2
egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/README.md
View File

@ -1 +1 @@
../../TEMPLATE/README.md
../TEMPLATE/README.md

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

@ -7,7 +7,7 @@ if __name__ == '__main__':
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,
)

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

@ -1 +1 @@
../../TEMPLATE/infer.py
../TEMPLATE/infer.py

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

@ -1 +1 @@
../../TEMPLATE/infer.sh
../TEMPLATE/infer.sh

2
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/README.md
View File

@ -1 +1 @@
../../TEMPLATE/README.md
../TEMPLATE/README.md

2
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/demo.py
View File

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

2
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/demo_online.py
View File

@ -11,7 +11,7 @@ if __name__ == '__main__':
inference_pipeline = pipeline(
task=Tasks.voice_activity_detection,
model="damo/speech_fsmn_vad_zh-cn-8k-common",
model_revision='v1.2.0',
model_revision=None,
output_dir=output_dir,
batch_size=1,
mode='online',

2
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py
View File

@ -1 +1 @@
../../TEMPLATE/infer.py
../TEMPLATE/infer.py

2
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.sh
View File

@ -1 +1 @@
../../TEMPLATE/infer.sh
../TEMPLATE/infer.sh

0
k2/__init__.py Normal file
View File