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

update readme

This commit is contained in:
nl 2018-07-26 10:41:00 +08:00
parent 18922dcd00
commit c09853f7a2
2 changed files with 20 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -1,7 +1,11 @@
# A Deep-Learning-Based Chinese Speech Recognition System
基于深度学习的中文语音识别系统
ReadMe Language [中文版](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README.md) [English](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README_EN.md)
[![GPL-3.0 Licensed](https://img.shields.io/badge/License-GPL3.0-blue.svg?style=flat)](https://opensource.org/licenses/GPL-3.0)
ReadMe Language 中文版 [English](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README_EN.md)
[查看本项目的Wiki页面](https://github.com/nl8590687/ASRT_SpeechRecognition/wiki) (正在完善中)
## Introduction 简介
@ -9,8 +13,6 @@ ReadMe Language [中文版](https://github.com/nl8590687/ASRT_SpeechRecognition/
This project uses Keras, TensorFlow based on deep convolutional neural network and long-short memory neural network, attention mechanism and CTC to implement.
[查看本项目的Wiki页面](https://github.com/nl8590687/ASRT_SpeechRecognition/wiki) (正在完善中)
本项目目前已经可以正常进行训练了。
通过git克隆仓库以后，需要将datalist目录下的文件全部拷贝到dataset目录下，也就是将其跟数据集放在一起。
@ -18,7 +20,7 @@ This project uses Keras, TensorFlow based on deep convolutional neural network a
$ cp -rf datalist/* dataset/
```
目前可用的模型有22、24和25
目前可用的模型有24、25和251
本项目开始训练请执行：
```shell
@ -49,7 +51,7 @@ CNN + LSTM/GRU + CTC
* 关于下载已经训练好的模型的问题
可以在Github本仓库下release里面的查看发布的各个版本软件的压缩包里获得完整源程序。
可以在Github本仓库下[releases](https://github.com/nl8590687/ASRT_SpeechRecognition/releases)里面的查看发布的各个版本软件的压缩包里获得完整源程序。
### Language Model 语言模型
@ -118,3 +120,5 @@ ST-CMDS-20170001_1-OS.tar.gz
@ZJUGuoShuai @williamchenwl
@nl8590687 (repo owner)
[打赏作者](https://github.com/nl8590687/ASRT_SpeechRecognition/wiki/donate)

14
README_EN.md
View File

@ -1,13 +1,15 @@
# A Deep-Learning-Based Chinese Speech Recognition System
ReadMe Language [中文版](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README.md) [English](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README_EN.md)
[![GPL-3.0 Licensed](https://img.shields.io/badge/License-GPL3.0-blue.svg?style=flat)](https://opensource.org/licenses/GPL-3.0)
ReadMe Language [中文版](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README.md) English
[View this project's wiki page](https://github.com/nl8590687/ASRT_SpeechRecognition/wiki) (In progress..)
## Introduction
This project uses Keras, TensorFlow based on deep convolutional neural network and long-short memory neural network, attention mechanism and CTC to implement.
[View this project's wiki page](https://github.com/nl8590687/ASRT_SpeechRecognition/wiki) (In progress..)
The project can now be properly trained.
After cloning a repository through git, you need to copy all the files in the datalist directory to the dataset directory, that is, put them together with the data set.
@ -16,7 +18,7 @@ After cloning a repository through git, you need to copy all the files in the da
$ cp -rf datalist/* dataset/
```
Currently available models are 22, 24 and 25
Currently available models are 24, 25 and 251
To start training this project, please execute:
```shell
@ -47,7 +49,7 @@ CNN + LSTM/GRU + CTC
* Questions about downloading trained models
The complete source program can be obtained from the archives of the various versions of the software released in the release page of Github.
The complete source program can be obtained from the archives of the various versions of the software released in the [releases](https://github.com/nl8590687/ASRT_SpeechRecognition/releases) page of Github.
### Language Model
@ -110,3 +112,5 @@ Links: [Progress Logs](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/
@ZJUGuoShuai @williamchenwl
@nl8590687 (repo owner)
[Donate](https://github.com/nl8590687/ASRT_SpeechRecognition/wiki/donate)