diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index 28a31a200..30ae8c990 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -102,20 +102,20 @@ print(rec_result)
 ### Inference with multi-thread CPUs or multi GPUs
 FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/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 `${data_dir}/text` is also exists, CER will be computed
-    - `output_dir`: output dir of the recognition results
-    - `batch_size`: `64` (Default), batch size of inference on gpu
-    - `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
-    - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
-    - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
-    - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
-    - `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
-    - `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast、normal、offline)
-    - `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
+#### Settings of `infer.sh`
+- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+- `data_dir`: the dataset dir needs to include `wav.scp`. If `${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
+- `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast、normal、offline)
+- `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
 
-- Decode with multi GPUs:
+#### Decode with multi GPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -125,7 +125,7 @@ FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.
     --gpu_inference true \
     --gpuid_list "0,1"
 ```
-- Decode with multi-thread CPUs:
+#### Decode with multi-thread CPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -135,7 +135,7 @@ FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.
     --njob 64
 ```
 
-- Results
+#### Results
 
 The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
 
diff --git a/egs_modelscope/punctuation/TEMPLATE/README.md b/egs_modelscope/punctuation/TEMPLATE/README.md
index 3eaf68a11..dfbe04480 100644
--- a/egs_modelscope/punctuation/TEMPLATE/README.md
+++ b/egs_modelscope/punctuation/TEMPLATE/README.md
@@ -70,17 +70,17 @@ Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/
 ### Inference with multi-thread CPUs or multi GPUs
 FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/punctuation/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs. It is an offline recipe and only support offline model.
 
-- 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 `punc.txt`
-    - `output_dir`: output dir of the recognition results
-    - `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, `punc.pb` (Default), which checkpoint is used to infer
+#### Settings of `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 `punc.txt`
+- `output_dir`: output dir of the recognition results
+- `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, `punc.pb` (Default), which checkpoint is used to infer
 
-- Decode with multi GPUs:
+#### Decode with multi GPUs:
 ```shell
     bash infer.sh \
     --model "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch" \
@@ -90,7 +90,7 @@ FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https:/
     --gpu_inference true \
     --gpuid_list "0,1"
 ```
-- Decode with multi-thread CPUs:
+#### Decode with multi-thread CPUs:
 ```shell
     bash infer.sh \
     --model "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch" \
@@ -100,7 +100,6 @@ FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https:/
     --njob 1
 ```
 
-
 ## Finetune with pipeline
 
 ### Quick start
diff --git a/egs_modelscope/tp/TEMPLATE/README.md b/egs_modelscope/tp/TEMPLATE/README.md
index d33d4e6d6..62c35d80a 100644
--- a/egs_modelscope/tp/TEMPLATE/README.md
+++ b/egs_modelscope/tp/TEMPLATE/README.md
@@ -61,18 +61,18 @@ Timestamp pipeline can also be used after ASR pipeline to compose complete ASR f
 ### Inference with multi-thread CPUs or multi GPUs
 FunASR also offer recipes [egs_modelscope/tp/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/tp/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 **must** include `wav.scp` and `text.txt`
-    - `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
+#### Settings of `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 **must** include `wav.scp` and `text.txt`
+- `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:
+#### Decode with multi GPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -82,7 +82,7 @@ FunASR also offer recipes [egs_modelscope/tp/TEMPLATE/infer.sh](https://github.c
     --gpu_inference true \
     --gpuid_list "0,1"
 ```
-- Decode with multi-thread CPUs:
+#### Decode with multi-thread CPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
diff --git a/egs_modelscope/vad/TEMPLATE/README.md b/egs_modelscope/vad/TEMPLATE/README.md
index 9ad9a1ce2..503b9bf8e 100644
--- a/egs_modelscope/vad/TEMPLATE/README.md
+++ b/egs_modelscope/vad/TEMPLATE/README.md
@@ -69,18 +69,18 @@ Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/
 ### Inference with multi-thread CPUs or multi GPUs
 FunASR also offer recipes [egs_modelscope/vad/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/vad/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
+#### Settings of `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:
+#### Decode with multi GPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -90,7 +90,7 @@ FunASR also offer recipes [egs_modelscope/vad/TEMPLATE/infer.sh](https://github.
     --gpu_inference true \
     --gpuid_list "0,1"
 ```
-- Decode with multi-thread CPUs:
+#### Decode with multi-thread CPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
index b6fa9378f..90e04bc44 100644
--- a/funasr/runtime/python/websocket/README.md
+++ b/funasr/runtime/python/websocket/README.md
@@ -51,12 +51,17 @@ cd funasr/runtime/python/websocket
 pip install -r requirements_client.txt
 ```
 
-Start client
-
+### Start client
+#### Recording from mircrophone
 ```shell
 # --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
 python ws_client.py --host "127.0.0.1" --port 10096 --chunk_size "5,10,5"
 ```
+#### Loadding from wav.scp(kaldi style)
+```shell
+# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
+python ws_client.py --host "127.0.0.1" --port 10096 --chunk_size "5,10,5" --audio_in "./data/wav.scp"
+```
 
 ## Acknowledge
 1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).