vad docs

游雁

2023-05-10 a85cfe4a31e99858cb4b7d41edfd75e808dba45a

vad docs

 egs_modelscope/vad/TEMPLATE/README.md

@@ -83,7 +83,7 @@
#### 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 @@
#### 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 \

 egs_modelscope/vad/TEMPLATE/infer.py

@@ -16,10 +16,10 @@

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)

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

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

 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,
    )

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

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

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

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

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

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

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

@@ -7,7 +7,7 @@
    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,
    )

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

@@ -11,7 +11,7 @@
    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',

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

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

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

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

 k2/__init__.py