ASRT_SpeechRecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

GPL-3.0 License

Downloads
67
Stars
7.8K
Committers
13

ASRT "Star" ~

ReadMe Language | | English |

ASRT | **** | Wiki | Demo | ****

issueQQ894112051 AIailemon-me ASRT

FAQ Issues

CPUGPUPythonTensorFlowCUDA

Introduction

tensorFlow.kerasCTC

  • CPU: 4 (x86_64, amd64) +
  • RAM: 16 GB +
  • GPU: NVIDIA, Graph Memory 11GB+ (1080ti)
  • : 500 GB ()

  • Linux: Ubuntu 20.04+ / CentOS 7+ (+) Windows: 10/11()
  • Python: 3.9 - 3.11
  • TensorFlow: 2.5 - 2.11

Linux

Git

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

"Fork" CopySSH

git /data/speech_data ()

Thchs30ST-CMDSPrimewordsaishell-1aidatatang200MagicData ASRT

$ cd ASRT_SpeechRecognition

$ mkdir /data/speech_data

$ tar zxf <> -C /data/speech_data/ 
$ python download_default_datalist.py

2425251251bn

Python3

$ python3 train_speech_model.py
$ python3 evaluate_speech_model.py
$ python3 predict_speech_file.py

ASRT HTTPAPI

$ python3 asrserver_http.py

HTTPAPI

$ python3 client_http.py

ASRT GRPCAPI

$ python3 asrserver_grpc.py

GRPCAPI

$ python3 client_grpc.py

APIASRTWikiASRTSDKDemo

251bn from speech_model.xxx import xxx

dockerASRT

$ 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

CPU

Model

Speech Model

DCNN + CTC

16

ASRT

GithubReleaseszip

Language Model

About Accuracy

85%

Python

  • tensorFlow (2.5-2.11+)
  • numpy
  • wave
  • matplotlib
  • scipy
  • requests
  • flask
  • waitress
  • grpcio / grpcio-tools / protobuf

(GPU Python3.9CUDA 11.2 cudnn 8.1)

$ pip install -r requirements.txt

Data Sets

THCHS30 40h 6.01G data_thchs30.tgz data_thchs30.tgz
ST-CMDS 100h 7.67G ST-CMDS-20170001_1-OS.tar.gz ST-CMDS-20170001_1-OS.tar.gz
AIShell-1 178h 14.51G data_aishell.tgz data_aishell.tgz
Primewords 100h 8.44G primewords_md_2018_set1.tar.gz primewords_md_2018_set1.tar.gz
MagicData 755h 52G/1.0G/2.2G train_set.tar.gz / dev_set.tar.gz / test_set.tar.gz train_set.tar.gz / dev_set.tar.gz / test_set.tar.gz

AISHELL-1

$ tar xzf data_aishell.tgz
$ cd data_aishell/wav
$ for tar in *.tar.gz;  do tar xvf $tar; done

OpenSLR

ASRTAPISDK

ASRTRPCSDKRESTful Open APIASRT

WindowsSDKDemo ASRT_SDK_WinClient
Python3SDKDemo ASRT_SDK_Python3
GolangSDKDemo asrt-sdk-go
JavaSDKDemo ASRT_SDK_Java

ASRT

ASRT

ASRT

CTC

AI

AI

License

GPL v3.0 nl8590687 AI

DOI: 10.5281/zenodo.5808434

Contributors

@nl8590687 (repo owner)

Package Rankings
Top 15.33% on Pypi.org
Top 9.78% on Proxy.golang.org
Badges
Extracted from project README
GPL-3.0 Licensed Stars TensorFlow Version Python Version DOI