diff --git a/Dockerfile b/Dockerfile
index 39e046a..dc6e933 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -30,16 +30,16 @@ RUN apt update && apt install -y python3 python3-pip
 
 RUN pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
 
-RUN pip3 install wave scipy matplotlib tensorflow-cpu==2.5.3 numpy==1.19.2 requests flask waitress grpcio grpcio-tools protobuf
+RUN pip3 install wave scipy matplotlib tensorflow-cpu==2.5.3 numpy==1.19.2 requests flask waitress grpcio==1.34.0 grpcio-tools==1.34.0 protobuf
 
-RUN echo $'cd /asrt_server \n python3 asrserver_http.py' > /asrt_server/start.sh && chmod +x /asrt_server/start.sh
+RUN echo $'cd /asrt_server \n python3 asrserver_http.py & \n python3 asrserver_grpc.py' > /asrt_server/start.sh && chmod +x /asrt_server/start.sh
 
 # refer: https://docs.docker.com/engine/reference/builder/#expose
-EXPOSE 20001/tcp
+EXPOSE 20001/tcp 20002/tcp
 
 ENTRYPOINT ["/bin/bash", "/asrt_server/start.sh"]
 
 # https://docs.docker.com/engine/reference/commandline/build/#options
 # docker build --progress plain --rm --build-arg TAG=1.3.0 --tag asrt/api_server:1.3.0 .
 # https://docs.docker.com/engine/reference/commandline/run/#options
-# docker run --rm -it  -p 20001:20001 --name asrt -d asrt/api_server:1.3.0
+# docker run --rm -it -p 20001:20001 -p 20002:20002 --name asrt -d asrt/api_server:1.3.0
diff --git a/README.md b/README.md
index 6cee01d..f79f2a7 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@
 [![GPL-3.0 Licensed](https://img.shields.io/badge/License-GPL3.0-blue.svg?style=flat)](https://opensource.org/licenses/GPL-3.0) 
 [![Stars](https://img.shields.io/github/stars/nl8590687/ASRT_SpeechRecognition)](https://github.com/nl8590687/ASRT_SpeechRecognition) 
 [![TensorFlow Version](https://img.shields.io/badge/Tensorflow-1.15+-blue.svg)](https://www.tensorflow.org/) 
-[![Python Version](https://img.shields.io/badge/Python-3.6+-blue.svg)](https://www.python.org/) 
+[![Python Version](https://img.shields.io/badge/Python-3.7+-blue.svg)](https://www.python.org/) 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5808434.svg)](https://doi.org/10.5281/zenodo.5808434)
 
 ASRT是一个基于深度学习的中文语音识别系统，如果您觉得喜欢，请点一个 **"Star"** 吧~
@@ -37,7 +37,7 @@ ASRT是一个基于深度学习的中文语音识别系统，如果您觉得喜
 
 ### 软件
 * Linux: Ubuntu 18.04 + / CentOS 7 +
-* Python: 3.6 +
+* Python: 3.7 +
 * TensorFlow: 1.15, 2.x + (不建议使用最新版和大版本的x.x.0版)
 
 ## 快速开始
@@ -87,24 +87,34 @@ $ python3 evaluate_speech_model.py
 $ python3 predict_speech_file.py
 ```
 
-ASRT API服务器启动请执行：
+启动ASRT HTTP协议的API服务器启动请执行：
 ```shell
 $ python3 asrserver_http.py
 ```
 
-本地测试调用API服务是否成功：
+本地测试调用HTTP协议API服务是否成功：
 ```shell
 $ python3 client_http.py
 ```
 
+启动ASRT GRPC协议的API服务器启动请执行：
+```shell
+$ python3 asrserver_grpc.py
+```
+
+本地测试调用GRPC协议API服务是否成功：
+```shell
+$ python3 client_grpc.py
+```
+
 请注意，开启API服务器之后，需要使用本ASRT项目对应的客户端软件来进行语音识别，详见Wiki文档[下载ASRT语音识别客户端SDK和Demo](https://wiki.ailemon.net/docs/asrt-doc/download)。
 
-如果要训练和使用非251bn版模型，请在代码中 `import speech_model_zoo` 的相应位置做修改。
+如果要训练和使用非251bn版模型，请在代码中 `from speech_model.xxx import xxx` 的相应位置做修改。
 
 使用docker直接部署ASRT：
 ```shell
-$ docker pull ailemondocker/asrt_service:1.2.0
-$ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.2.0
+$ docker pull ailemondocker/asrt_service:1.3.0
+$ docker run --rm -it -p 20001:20001 -p 20002:20002 --name asrt-server -d ailemondocker/asrt_service:1.3.0
 ```
 仅CPU运行推理识别，不作训练
 
@@ -143,6 +153,7 @@ Github本仓库下[Releases](https://github.com/nl8590687/ASRT_SpeechRecognition
 * requests
 * flask
 * waitress
+* grpcio / grpcio-tools / protobuf
 
 不会安装环境的同学请直接运行以下命令(前提是有GPU且已经安装好 CUDA 11.2 和 cudnn 8.1)：
 
diff --git a/README_EN.md b/README_EN.md
index 7b40fcf..5d758cc 100644
--- a/README_EN.md
+++ b/README_EN.md
@@ -3,7 +3,7 @@
 [![GPL-3.0 Licensed](https://img.shields.io/badge/License-GPL3.0-blue.svg?style=flat)](https://opensource.org/licenses/GPL-3.0) 
 [![Stars](https://img.shields.io/github/stars/nl8590687/ASRT_SpeechRecognition)](https://github.com/nl8590687/ASRT_SpeechRecognition) 
 [![TensorFlow Version](https://img.shields.io/badge/Tensorflow-1.15+-blue.svg)](https://www.tensorflow.org/) 
-[![Python Version](https://img.shields.io/badge/Python-3.6+-blue.svg)](https://www.python.org/) 
+[![Python Version](https://img.shields.io/badge/Python-3.7+-blue.svg)](https://www.python.org/) 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5808434.svg)](https://doi.org/10.5281/zenodo.5808434)
 
 ASRT is A Deep-Learning-Based Chinese Speech Recognition System. If you like this project, please **star** it. 
@@ -35,7 +35,7 @@ This project uses tensorFlow.keras based on deep convolutional neural network an
 
 ### Software
 * Linux: Ubuntu 18.04 + / CentOS 7 +
-* Python: 3.6 +
+* Python: 3.7 +
 * TensorFlow: 1.15, 2.x + (The latest and x.x.0 are deprecated)
 
 ## Quick Start
@@ -84,7 +84,7 @@ To predict one wave audio file for speech recognition：
 $ python3 predict_speech_file.py
 ```
 
-ASRT API Server startup please execute:
+To startup ASRT API Server with HTTP protocol please execute:
 ```shell
 $ python3 asrserver_http.py
 ```
@@ -92,19 +92,29 @@ $ python3 asrserver_http.py
 Please note that after opening the API server, you need to use the client software corresponding to this ASRT project for voice recognition. For details, see the Wiki documentation to [download ASRT Client SDK & Demo](https://wiki.ailemon.net/docs/asrt-doc/download).
 
 
-To test whether it is successful or not that calls api service interface:
+To test whether it is successful or not that calls api service interface with HTTP protocol:
 ```shell
 $ python3 client_http.py
 ```
 
-If you want to train and use other model(not Model 251bn), make changes in the corresponding position of the `import speech_model_zoo` in the code files.
+To startup ASRT API Server with GRPC protocol please execute:
+```shell
+$ python3 asrserver_grpc.py
+```
+
+To test whether it is successful or not that calls api service interface with GRPC protocol:
+```shell
+$ python3 client_grpc.py
+```
+
+If you want to train and use other model(not Model 251bn), make changes in the corresponding position of the `from speech_model.xxx import xxx` in the code files.
 
 If there is any problem during the execution of the program or during use, it can be promptly put forward in the issue, and I will reply as soon as possible.
 
 Deploy ASRT by docker：
 ```shell
-$ docker pull ailemondocker/asrt_service:1.2.0
-$ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.2.0
+$ docker pull ailemondocker/asrt_service:1.3.0
+$ docker run --rm -it -p 20001:20001 -p 20002:20002 --name asrt-server -d ailemondocker/asrt_service:1.3.0
 ```
 It will start a api server for recognition rather than training.
 
@@ -143,6 +153,7 @@ At present, the best model can basically reach 85% of Pinyin correct rate on the
 * requests
 * flask
 * waitress
+* grpcio / grpcio-tools / protobuf
 
 If you have trouble when install those packages, please run the following script to do it as long as you have a GPU and CUDA 11.2 and cudnn 8.1 have been installed：