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
ASRT "Star" ~
ReadMe Language | | English |
ASRT | **** | Wiki | Demo | ****
issueQQ894112051 AIailemon-me ASRT
CPUGPUPythonTensorFlowCUDA
tensorFlow.kerasCTC
Linux
$ 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 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
DCNN + CTC
16
GithubReleaseszip
85%
(GPU Python3.9CUDA 11.2 cudnn 8.1)
$ pip install -r requirements.txt
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
ASRTRPCSDKRESTful Open APIASRT
WindowsSDKDemo | ASRT_SDK_WinClient |
Python3SDKDemo | ASRT_SDK_Python3 |
GolangSDKDemo | asrt-sdk-go |
JavaSDKDemo | ASRT_SDK_Java |
ASRT
ASRT
CTC
@nl8590687 (repo owner)