vad docs

游雁

2023-04-21 7ca311f847a077cfea702762037ea17ce92a39cf

vad docs

 docs/modescope_pipeline/vad_pipeline.md

New file
@@ -0,0 +1 @@
../../egs_modelscope/vad/TEMPLATE/README.md

 egs_modelscope/vad/TEMPLATE/README.md

File was renamed from docs/modescope_pipeline/vad_pipeline.md
@@ -71,7 +71,7 @@

- Setting parameters in `infer.sh`
    - `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
    - `data_dir`: the dataset dir needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
    - `data_dir`: the dataset dir needs to include `wav.scp`
    - `output_dir`: output dir of the recognition results
    - `batch_size`: `64` (Default), batch size of inference on gpu
    - `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
@@ -99,7 +99,6 @@
    --gpu_inference false \
    --njob 64
```


## Finetune with pipeline


 egs_modelscope/vad/TEMPLATE/infer.py

New file
@@ -0,0 +1,25 @@
import os
import shutil
import argparse
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

def modelscope_infer(args):
    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
    inference_pipeline = pipeline(
        task=Tasks.voice_activity_detection,
        model=args.model,
        output_dir=args.output_dir,
        batch_size=args.batch_size,
    )
    inference_pipeline(audio_in=args.audio_in)

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('--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('--gpuid', type=str, default="0")
    args = parser.parse_args()
    modelscope_infer(args)

 egs_modelscope/vad/TEMPLATE/infer.sh

New file
@@ -0,0 +1,71 @@
#!/usr/bin/env bash

set -e
set -u
set -o pipefail

stage=1
stop_stage=2
model="damo/speech_fsmn_vad_zh-cn-16k-common"
data_dir="./data/test"
output_dir="./results"
batch_size=64
gpu_inference=true    # whether to perform gpu decoding
gpuid_list="0,1"    # set gpus, e.g., gpuid_list="0,1"
njob=64    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
checkpoint_dir=
checkpoint_name="valid.cer_ctc.ave.pb"

. utils/parse_options.sh || exit 1;

if ${gpu_inference} == "true"; then
    nj=$(echo $gpuid_list | awk -F "," '{print NF}')
else
    nj=$njob
    batch_size=1
    gpuid_list=""
    for JOB in $(seq ${nj}); do
        gpuid_list=$gpuid_list"-1,"
    done
fi

mkdir -p $output_dir/split
split_scps=""
for JOB in $(seq ${nj}); do
    split_scps="$split_scps $output_dir/split/wav.$JOB.scp"
done
perl utils/split_scp.pl ${data_dir}/wav.scp ${split_scps}

if ${checkpoint_dir}; then
  python utils/prepare_checkpoint.py ${model} ${checkpoint_dir} ${checkpoint_name}
  model=${checkpoint_dir}/${model}
fi

if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
    echo "Decoding ..."
    gpuid_list_array=(${gpuid_list//,/ })
    for JOB in $(seq ${nj}); do
        {
        id=$((JOB-1))
        gpuid=${gpuid_list_array[$id]}
        mkdir -p ${output_dir}/output.$JOB
        python infer.py \
            --model ${model} \
            --audio_in ${output_dir}/split/wav.$JOB.scp \
            --output_dir ${output_dir}/output.$JOB \
            --batch_size ${batch_size} \
            --gpuid ${gpuid}
        }&
    done
    wait

    mkdir -p ${output_dir}/1best_recog
    for f in token score text; do
        if [ -f "${output_dir}/output.1/1best_recog/${f}" ]; then
          for i in $(seq "${nj}"); do
              cat "${output_dir}/output.${i}/1best_recog/${f}"
          done | sort -k1 >"${output_dir}/1best_recog/${f}"
        fi
    done
fi


 egs_modelscope/vad/TEMPLATE/utils

New file
@@ -0,0 +1 @@
../../../egs/aishell/transformer/utils