OrgLion-ML
/
ASRT_SpeechRecognition
mirror of https://github.com/nl8590687/ASRT_SpeechRecognition.git
1
0
Fork 0
Code Issues Releases Wiki Activity

更新版本信息和脚本

This commit is contained in:
ailemon 2022-05-24 20:46:06 +08:00
parent c4e668fcf4
commit 821dbf34ba
3 changed files with 40 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Dockerfile
View File

@ -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 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 # refer: https://docs.docker.com/engine/reference/builder/#expose
EXPOSE 20001/tcp EXPOSE 20001/tcp 20002/tcp
ENTRYPOINT ["/bin/bash", "/asrt_server/start.sh"] ENTRYPOINT ["/bin/bash", "/asrt_server/start.sh"]
# https://docs.docker.com/engine/reference/commandline/build/#options # 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 . # 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 # 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

25
README.md
View File

@ -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) [![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) [![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/) [![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) [![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~ 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 ### 软件
* Linux: Ubuntu 18.04 + / CentOS 7 + * 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) * 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 ## 快速开始
@ -87,24 +87,34 @@ $ python3 evaluate_speech_model.py
$ python3 predict_speech_file.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 ```shell
$ python3 asrserver_http.py $ 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 ```shell
$ python3 client_http.py $ 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)。 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： 使用docker直接部署ASRT：
```shell ```shell
$ docker pull ailemondocker/asrt_service:1.2.0 $ docker pull ailemondocker/asrt_service:1.3.0
$ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.2.0 $ 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 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 * requests
* flask * flask
* waitress * 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)： 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)：

25
README_EN.md
View File

@ -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) [![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) [![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/) [![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) [![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. 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 ### Software
* Linux: Ubuntu 18.04 + / CentOS 7 + * 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) * TensorFlow: 1.15, 2.x + (The latest and x.x.0 are deprecated)
## Quick Start ## Quick Start
@ -84,7 +84,7 @@ To predict one wave audio file for speech recognition：
$ python3 predict_speech_file.py $ python3 predict_speech_file.py
``` ```
ASRT API Server startup please execute: To startup ASRT API Server with HTTP protocol please execute:
```shell ```shell
$ python3 asrserver_http.py $ 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). 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 ```shell
$ python3 client_http.py $ 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. 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： Deploy ASRT by docker：
```shell ```shell
$ docker pull ailemondocker/asrt_service:1.2.0 $ docker pull ailemondocker/asrt_service:1.3.0
$ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.2.0 $ 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. 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 * requests
* flask * flask
* waitress * 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： 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：