(C) 2018 aiLemon

ASRT

A Deep-Learning-Based Chinese Speech Recognition System

What is ASRT?

This project is a deep-learning-based Chinese speech recognition system, which uses Keras, TensorFlow based on deep convolutional neural network and CTC for speech model and Maximum entropy hidden Markov model for language model to implement. And also, we provide a hTTP-based server software to setup a API server easily for other clients to send API requests.

Developed for research

This is a project to research on Speech Recognition. We hope it can be a high accuracy ASR system.

Time saver

It can save your time to download released software and run a ASR server for your applications.

Cross-platform

You can run this ASR server on Windows, Linux or MacOS as long as there are python 3 installed in machine. Your client applications can also run in all platform with Internet connected.

Deep-Learning-Based

This project use neural network model based CTC to implement and made a good correct rate.

Easy to modify

This project is highly encapsulated and all components is componentized. You can build a ASR system like building blocks.

LESS files included

There are a little files in this project and you can build a ASR system as usually.

Features

Get Started

Clone or Download

If you want to build a ASR system server please click here to download the latest version.

If you want to train your own models or modify models to train please follow these steps to do.

  • Environment: Python3, Git
  • Package: TensorFlow, Keras, Wave and so on
  • Languages: Python

    $ git clone https://github.com/nl8590687/ASRT_SpeechRecognition.git
                     

Download Speech Data Set

This project use THCHS30 and ST-CMDS speech data set. You can download them Here. For people in China, you can download them more quickly from This.

After cloning a repository through git and downloading data set, you need to copy all the files in the datalist directory to the dataset directory, that is, put them together with the data set.

    
    $ cp -rf datalist/* dataset/
    

Run

To start training this project, please execute:


    $ python3 train_mspeech.py
                    

ASRT API Server startup please execute:


    $ python3 asrserver.py
                    

Full Documentation

For more information you can click the following button to see full documentation.

More on GitHub

License

This project is made by GitHub user nl8590687 at GitHub for developers and is 100% FREE under the GNU General Public License v3.0(GPL v3.0) License.

If you are feeling generous and want to show your support to ASRT project, you can buy him a beer or coffee via the AliPay and Wechat donate QR code below. :)

AliPay
WeChat

Contact

I hope you find this ASRT speech recognition project useful.
Feel free to get in touch if you have any questions or suggestions.

Get Connected