diff --git a/demos/custom_streaming_asr/README.md b/demos/custom_streaming_asr/README.md
index 5d94856f..aa28d502 100644
--- a/demos/custom_streaming_asr/README.md
+++ b/demos/custom_streaming_asr/README.md
@@ -7,39 +7,40 @@ In some cases, we need to recognize the specific rare words with high accuracy.
 
 this demo is customized for expense account, which need to recognize rare address.
 
-* G with slot: 打车到 "address_slot"。
+* G with slot: 打车到 "address_slot"。  
 ![](https://ai-studio-static-online.cdn.bcebos.com/28d9ef132a7f47a895a65ae9e5c4f55b8f472c9f3dd24be8a2e66e0b88b173a4)
 
-* this is address slot wfst, you can add the address which want to recognize.
+* this is address slot wfst, you can add the address which want to recognize.  
 ![](https://ai-studio-static-online.cdn.bcebos.com/47c89100ef8c465bac733605ffc53d76abefba33d62f4d818d351f8cea3c8fe2)
 
-* after replace operation, G = fstreplace(G_with_slot, address_slot), we will get the customized graph.
+* after replace operation, G = fstreplace(G_with_slot, address_slot), we will get the customized graph.  
 ![](https://ai-studio-static-online.cdn.bcebos.com/60a3095293044f10b73039ab10c7950d139a6717580a44a3ba878c6e74de402b)  
 
 ## Usage
 ### 1. Installation
 install paddle:2.2.2 docker.
 ```
-sudo nvidia-docker pull registry.baidubce.com/paddlepaddle/paddle:2.2.2
+sudo docker pull registry.baidubce.com/paddlepaddle/paddle:2.2.2
 
-sudo nvidia-docker run --privileged  --net=host --ipc=host -it --rm -v $PWD:/paddle --name=paddle_demo_docker registry.baidubce.com/paddlepaddle/paddle:2.2.2 /bin/bash 
+sudo docker run --privileged  --net=host --ipc=host -it --rm -v $PWD:/paddle --name=paddle_demo_docker registry.baidubce.com/paddlepaddle/paddle:2.2.2 /bin/bash 
 ```
 
 ### 2. demo
 * run websocket_server.sh.  This script will download resources and libs, and launch the service.
 ```
+cd /paddle
 bash websocket_server.sh
 ```
-this script run in two steps:
-1. download the resources.tar.gz, those direcotries will be found in resource directory.
-model: acustic model
+this script run in two steps:  
+1. download the resources.tar.gz, those direcotries will be found in resource directory.  
+model: acustic model  
 graph: the decoder graph (TLG.fst)  
 lib: some libs  
 bin: binary  
-data: audio and wav.scp
+data: audio and wav.scp  
 
-2. websocket_server_main launch the service.
-some params:
+2. websocket_server_main launch the service.  
+some params:  
 port: the service port  
 graph_path: the decoder graph path  
 model_path: acustic model path  
diff --git a/demos/custom_streaming_asr/README_cn.md b/demos/custom_streaming_asr/README_cn.md
index 209b882e..cd8893af 100644
--- a/demos/custom_streaming_asr/README_cn.md
+++ b/demos/custom_streaming_asr/README_cn.md
@@ -6,45 +6,45 @@
 
 这个 demo 是打车报销单的场景识别，需要识别一些稀有的地名，可以通过如下操作实现。
 
-* G with slot: 打车到 "address_slot"。
+* G with slot: 打车到 "address_slot"。  
 ![](https://ai-studio-static-online.cdn.bcebos.com/28d9ef132a7f47a895a65ae9e5c4f55b8f472c9f3dd24be8a2e66e0b88b173a4)
 
-* 这是address slot wfst, 可以添加一些需要识别的地名.
+* 这是address slot wfst, 可以添加一些需要识别的地名.  
 ![](https://ai-studio-static-online.cdn.bcebos.com/47c89100ef8c465bac733605ffc53d76abefba33d62f4d818d351f8cea3c8fe2)
 
-* 通过replace 操作, G = fstreplace(G_with_slot, address_slot), 最终可以得到定制化的解码图。
+* 通过replace 操作, G = fstreplace(G_with_slot, address_slot), 最终可以得到定制化的解码图。  
 ![](https://ai-studio-static-online.cdn.bcebos.com/60a3095293044f10b73039ab10c7950d139a6717580a44a3ba878c6e74de402b)  
 
 ## 使用方法
 ### 1. 配置环境
 安装paddle:2.2.2 docker镜像。
 ```
-sudo nvidia-docker pull registry.baidubce.com/paddlepaddle/paddle:2.2.2
+sudo docker pull registry.baidubce.com/paddlepaddle/paddle:2.2.2
 
-sudo nvidia-docker run --privileged  --net=host --ipc=host -it --rm -v $PWD:/paddle --name=paddle_demo_docker registry.baidubce.com/paddlepaddle/paddle:2.2.2 /bin/bash 
+sudo docker run --privileged  --net=host --ipc=host -it --rm -v $PWD:/paddle --name=paddle_demo_docker registry.baidubce.com/paddlepaddle/paddle:2.2.2 /bin/bash 
 ```
 
 ### 2. 演示
 * 运行如下命令，完成相关资源和库的下载和服务启动。
 ```
+cd /paddle
 bash websocket_server.sh
 ```
 上面脚本完成了如下两个功能：
-1. 完成resource.tar.gz下载，解压后,会在resource中发现如下目录：
-model: 声学模型
-graph: 解码构图
-lib: 相关库
-bin: 运行程序
-data: 语音数据
+1. 完成resource.tar.gz下载，解压后,会在resource中发现如下目录：  
+model: 声学模型  
+graph: 解码构图  
+lib: 相关库  
+bin: 运行程序  
+data: 语音数据  
 
 2. 通过websocket_server_main来启动服务。
-这里简单的介绍几个参数:
-port是服务端口，
-graph_path用来指定解码图文件，
-model相关参数用来指定声学模型文件。
-其他参数说明可参见代码：
-PaddleSpeech/speechx/speechx/decoder/param.h
-PaddleSpeech/speechx/examples/ds2_ol/websocket/websocket_server_main.cc
+这里简单的介绍几个参数:  
+port是服务端口，  
+graph_path用来指定解码图文件，  
+其他参数说明可参见代码：  
+PaddleSpeech/speechx/speechx/decoder/param.h  
+PaddleSpeech/speechx/examples/ds2_ol/websocket/websocket_server_main.cc  
 
 * 在另一个终端中， 通过client发送数据，得到结果。运行如下命令：
 ```