diff --git a/docs/modescope_pipeline/vad_pipeline.md b/docs/modescope_pipeline/vad_pipeline.md
deleted file mode 100644
index ca8a5ee10..000000000
--- a/docs/modescope_pipeline/vad_pipeline.md
+++ /dev/null
@@ -1,111 +0,0 @@
-# Voice Activity Detection
-
-> **Note**: 
-> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take model of FSMN-VAD as example to demonstrate the usage.
-
-## Inference
-
-### Quick start
-#### [FSMN-VAD model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary)
-```python
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-inference_pipeline = pipeline(
-    task=Tasks.voice_activity_detection,
-    model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
-)
-
-segments_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav')
-print(segments_result)
-```
-#### [FSMN-VAD-online model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary)
-```python
-inference_pipeline = pipeline(
-    task=Tasks.auto_speech_recognition,
-    model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
-    )
-import soundfile
-speech, sample_rate = soundfile.read("example/asr_example.wav")
-
-param_dict = {"in_cache": dict(), "is_final": False}
-chunk_stride = 1600# 100ms
-# first chunk, 100ms
-speech_chunk = speech[0:chunk_stride] 
-rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
-print(rec_result)
-# next chunk, 480ms
-speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
-rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
-print(rec_result)
-```
-Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/236)
-
-
-
-#### API-reference
-##### Define pipeline
-- `task`: `Tasks.auto_speech_recognition`
-- `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
-- `ngpu`: `1` (Defalut), decoding on GPU. If ngpu=0, decoding on CPU
-- `ncpu`: `1` (Defalut), sets the number of threads used for intraop parallelism on CPU 
-- `output_dir`: `None` (Defalut), the output path of results if set
-- `batch_size`: `1` (Defalut), batch size when decoding
-##### Infer pipeline
-- `audio_in`: the input to decode, which could be: 
-  - wav_path, `e.g.`: asr_example.wav,
-  - pcm_path, `e.g.`: asr_example.pcm, 
-  - audio bytes stream, `e.g.`: bytes data from a microphone
-  - audio sample point，`e.g.`: `audio, rate = soundfile.read("asr_example_zh.wav")`, the dtype is numpy.ndarray or torch.Tensor
-  - wav.scp, kaldi style wav list (`wav_id \t wav_path``), `e.g.`: 
-  ```text
-  asr_example1  ./audios/asr_example1.wav
-  asr_example2  ./audios/asr_example2.wav
-  ```
-  In this case of `wav.scp` input, `output_dir` must be set to save the output results
-- `audio_fs`: audio sampling rate, only set when audio_in is pcm audio
-- `output_dir`: None (Defalut), the output path of results if set
-
-### Inference with multi-thread CPUs or multi GPUs
-FunASR also offer recipes [infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
-
-- 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
-    - `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
-    - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
-    - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
-    - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
-    - `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
-
-- Decode with multi GPUs:
-```shell
-    bash infer.sh \
-    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-    --data_dir "./data/test" \
-    --output_dir "./results" \
-    --batch_size 64 \
-    --gpu_inference true \
-    --gpuid_list "0,1"
-```
-- Decode with multi-thread CPUs:
-```shell
-    bash infer.sh \
-    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-    --data_dir "./data/test" \
-    --output_dir "./results" \
-    --gpu_inference false \
-    --njob 64
-```
-
-
-## Finetune with pipeline
-
-### Quick start
-
-### Finetune with your data
-
-## Inference with your finetuned model
-
diff --git a/docs/modescope_pipeline/vad_pipeline.md b/docs/modescope_pipeline/vad_pipeline.md
new file mode 120000
index 000000000..30ea6fc1e
--- /dev/null
+++ b/docs/modescope_pipeline/vad_pipeline.md
@@ -0,0 +1 @@
+../../egs_modelscope/vad/TEMPLATE/README.md
\ No newline at end of file
diff --git a/egs_modelscope/vad/TEMPLATE/README.md b/egs_modelscope/vad/TEMPLATE/README.md
new file mode 100644
index 000000000..84601b01a
--- /dev/null
+++ b/egs_modelscope/vad/TEMPLATE/README.md
@@ -0,0 +1,110 @@
+# Voice Activity Detection
+
+> **Note**: 
+> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take model of FSMN-VAD as example to demonstrate the usage.
+
+## Inference
+
+### Quick start
+#### [FSMN-VAD model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.voice_activity_detection,
+    model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+)
+
+segments_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav')
+print(segments_result)
+```
+#### [FSMN-VAD-online model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary)
+```python
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+    )
+import soundfile
+speech, sample_rate = soundfile.read("example/asr_example.wav")
+
+param_dict = {"in_cache": dict(), "is_final": False}
+chunk_stride = 1600# 100ms
+# first chunk, 100ms
+speech_chunk = speech[0:chunk_stride] 
+rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
+print(rec_result)
+# next chunk, 480ms
+speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
+rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
+print(rec_result)
+```
+Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/236)
+
+
+
+#### API-reference
+##### Define pipeline
+- `task`: `Tasks.auto_speech_recognition`
+- `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
+- `ngpu`: `1` (Defalut), decoding on GPU. If ngpu=0, decoding on CPU
+- `ncpu`: `1` (Defalut), sets the number of threads used for intraop parallelism on CPU 
+- `output_dir`: `None` (Defalut), the output path of results if set
+- `batch_size`: `1` (Defalut), batch size when decoding
+##### Infer pipeline
+- `audio_in`: the input to decode, which could be: 
+  - wav_path, `e.g.`: asr_example.wav,
+  - pcm_path, `e.g.`: asr_example.pcm, 
+  - audio bytes stream, `e.g.`: bytes data from a microphone
+  - audio sample point，`e.g.`: `audio, rate = soundfile.read("asr_example_zh.wav")`, the dtype is numpy.ndarray or torch.Tensor
+  - wav.scp, kaldi style wav list (`wav_id \t wav_path``), `e.g.`: 
+  ```text
+  asr_example1  ./audios/asr_example1.wav
+  asr_example2  ./audios/asr_example2.wav
+  ```
+  In this case of `wav.scp` input, `output_dir` must be set to save the output results
+- `audio_fs`: audio sampling rate, only set when audio_in is pcm audio
+- `output_dir`: None (Defalut), the output path of results if set
+
+### Inference with multi-thread CPUs or multi GPUs
+FunASR also offer recipes [infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
+
+- 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`
+    - `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
+    - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
+    - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
+    - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
+    - `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
+
+- Decode with multi GPUs:
+```shell
+    bash infer.sh \
+    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+    --data_dir "./data/test" \
+    --output_dir "./results" \
+    --batch_size 64 \
+    --gpu_inference true \
+    --gpuid_list "0,1"
+```
+- Decode with multi-thread CPUs:
+```shell
+    bash infer.sh \
+    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+    --data_dir "./data/test" \
+    --output_dir "./results" \
+    --gpu_inference false \
+    --njob 64
+```
+
+## Finetune with pipeline
+
+### Quick start
+
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/egs_modelscope/vad/TEMPLATE/infer.py b/egs_modelscope/vad/TEMPLATE/infer.py
new file mode 100644
index 000000000..3d9ee5520
--- /dev/null
+++ b/egs_modelscope/vad/TEMPLATE/infer.py
@@ -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)
\ No newline at end of file
diff --git a/egs_modelscope/vad/TEMPLATE/infer.sh b/egs_modelscope/vad/TEMPLATE/infer.sh
new file mode 100644
index 000000000..261b5e66b
--- /dev/null
+++ b/egs_modelscope/vad/TEMPLATE/infer.sh
@@ -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
+
diff --git a/egs_modelscope/vad/TEMPLATE/utils b/egs_modelscope/vad/TEMPLATE/utils
new file mode 120000
index 000000000..dc7d4171f
--- /dev/null
+++ b/egs_modelscope/vad/TEMPLATE/utils
@@ -0,0 +1 @@
+../../../egs/aishell/transformer/utils
\ No newline at end of file