Easy-to-use Speech Toolkit including SOTA/Streaming ASR with punctuation, influential TTS with text frontend, Speaker Verification System and End-to-End Speech Simultaneous Translation.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
Go to file
Hui Zhang 18567ced16
Update issue templates
4 years ago
.github Update issue templates 4 years ago
.notebook Support paddle 2.x (#538) 4 years ago
.pre-commit-hooks add pre commit hooks 4 years ago
.travis fix doc link and enhance install (#570) 4 years ago
deepspeech batch average ctc loss (#567) 4 years ago
docs fix doc link and enhance install (#570) 4 years ago
examples batch average ctc loss (#567) 4 years ago
tests Support paddle 2.x (#538) 4 years ago
tools Support paddle 2.x (#538) 4 years ago
utils fix doc link and enhance install (#570) 4 years ago
.clang-format Add ci and code format checking. 7 years ago
.gitignore Support paddle 2.x (#538) 4 years ago
.pre-commit-config.yaml Support paddle 2.x (#538) 4 years ago
.style.yapf Add ci and code format checking. 7 years ago
.travis.yml Support paddle 2.x (#538) 4 years ago
LICENSE Create License 7 years ago
README.md fix doc link and enhance install (#570) 4 years ago
README_cn.md fix doc link and enhance install (#570) 4 years ago
env.sh Support paddle 2.x (#538) 4 years ago
requirements.txt Refactor CTC module, add embedding and fix log (#549) 4 years ago
setup.sh fix doc link and enhance install (#570) 4 years ago

README.md

中文版

DeepSpeech on PaddlePaddle

License python version support os

DeepSpeech on PaddlePaddle is an open-source implementation of end-to-end Automatic Speech Recognition (ASR) engine, with PaddlePaddle platform. Our vision is to empower both industrial application and academic research on speech recognition, via an easy-to-use, efficient and scalable implementation, including training, inference & testing module, and demo deployment.

Models

Setup

  • python>=3.7
  • paddlepaddle>=2.0.0

Please see install.

Getting Started

Please see Getting Started and tiny egs.

More Information

Questions and Help

You are welcome to submit questions and bug reports in Github Issues. You are also welcome to contribute to this project.

License

DeepSpeech is provided under the Apache-2.0 License.