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.

tts conformer speech-translation voice-recognition sound-classification transformer asr speech-synthesis voice-cloning punctuation-restoration streaming-tts speech-recognition vocoder kws streaming-asr speech-alignment

Go to file

Hui Zhang b3c5104499 fix wget		5 years ago
.github	…
.pre-commit-hooks	…
.travis	…
deepspeech	Merge pull request #916 from PaddlePaddle/decoder	5 years ago
docs	fix img link; rsl format;	5 years ago
examples	fix img link; rsl format;	5 years ago
hub	…
parakeet	setup.py deps from requirements.txt	5 years ago
speechnn	…
tests	fix the bug of benchmark after merge the parakeet, add the condition of using kaldi in aishll s1	5 years ago
third_party	…
tools	fix wget	5 years ago
utils	Merge pull request #908 from PaddlePaddle/speech	5 years ago
.bashrc	…
.clang-format	…
.flake8	…
.gitconfig	…
.gitignore	setup with ubuntu deps	5 years ago
.mergify.yml	…
.pre-commit-config.yaml	…
.readthedocs.yml	merge parakeet repo into deepspeech	5 years ago
.style.yapf	…
.travis.yml	…
.vimrc	…
LICENSE	…
README.md	update readme	5 years ago
env.sh	fix env.sh PATH postion	5 years ago
requirements.txt	setup.py install cpp deps	5 years ago
setup.cfg	setup.py install cpp deps	5 years ago
setup.py	using setup.py to install pkgs by shell script	5 years ago
setup.sh	setup with ubuntu deps	5 years ago

README.md

PaddlePaddle Speech toolkit

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

Features

See feature list for more information.

Setup

All tested under:

Ubuntu 16.04
python>=3.7
paddlepaddle==2.1.2

Please see install.

Getting Started

Please see Getting Started and tiny egs.

More Information

Questions and Help

You are welcome to submit questions in Github Discussions 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.

Acknowledgement

We depends on many open source repos. See References for more information.