update readme

demos/custom_streaming_asr/README.md

@@ -1 +1,16 @@
-run setup_docker.sh first and then run websocket_server.sh
+([简体中文](./README_cn.md)|English)
+
+# Customized Auto Speech Recognition
+
+## introduction
+In some cases, we need to recognize the specific sentence with high accuracy. eg: customized keyword spotting, address recognition in navigation apps . customized ASR can slove those issues.
+
+this demo is customized for expense account of taxi, which need to recognize rare address.
+
+## Usage
+### 1. Installation
+Install docker by runing script setup_docker.sh. And then, install tmux (apt-get install tmux).
+
+### 2. demo
+* bash websocket_server.sh.  This script will download resources and libs, and then setup the server.
+* In the other terminal of docker, run script websocket_client.sh, the client will send data and get the results.

demos/custom_streaming_asr/README_cn.md

@@ -0,0 +1,18 @@
+(简体中文|[English](./README.md)
+
+# 定制化语音识别演示
+## 介绍
+定制化的语音识别是满足一些特定场景的语句识别的技术。
+
+可以参见简单的教程：
+https://aistudio.baidu.com/aistudio/projectdetail/3986429
+
+这个 demo 是打车报销单的场景识别，定制化了地点。
+
+## 使用方法
+### 1. 配置环境
+请通过 setup_docker.sh 安装镜像。进入镜像后，安装tmux (apt-get install tmux)，方便后续演示。
+
+### 2. 演示
+* bash websocket_server.sh, 完成相关资源和库的下载。这时候服务已经启动。
+* 在镜像另一个终端中，bash websocket_client.sh， 通过client发送数据，得到结果。