End-to-end Speech Processing toolkit
ESPnet is the state-of-the-art toolkit that covers end-to-end speech recognition, text-to-speech, speech translation, speech enhancement, speaker diarization, spoken language understanding, and much more!
Get started with ESPnet!
pip install espnet espnet-model-zoo and start using it immediately.
pip install espnet and use the espnetez module for fine-tuning.
Complete the full installation and use the existing recipes.
Comprehensive Task Coverage
We offer complete recipes for a wide range of speech processing tasks.
Tutorials
Leveraging ESPnet2 recipes for full replication
Documents on ESPnet1 recipes (Legacy)
Understanding and updating training configurations
Various tips for using run.sh in ESPnet recipes
Formatting audio files into wav.scp for ESPnet recipes
Common task/data interface for ESPnet2
Running ESPnet with Docker
Distributing jobs in a multi-machine environment
Handling multiple GPUs for training
Details on fixing the ESPnet documentation
How to cite ESPnet
@inproceedings{watanabe18_interspeech,
title = {ESPnet: End-to-End Speech Processing Toolkit},
author = {Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson {Enrique Yalta Soplin} and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
year = {2018},
booktitle = {Proc. Interspeech},
pages = {2207--2211},
doi = {10.21437/Interspeech.2018-1456},
issn = {2958-1796},
}To cite individual modules, models, or recipes, please refer to Additional Citations.