March 14, 2019

320 words 2 mins read



Facebook AI Research’s Automatic Speech Recognition Toolkit

repo name facebookresearch/wav2letter
repo link
language C++
size (curr.) 4266 kB
stars (curr.) 4934
created 2017-11-20
license Other



wav2letter++ is a fast, open source speech processing toolkit from the Speech team at Facebook AI Research built to facilitate research in end-to-end models for speech recognition. It is written entirely in C++ and uses the ArrayFire tensor library and the flashlight machine learning library for maximum efficiency. Our approach is detailed in this arXiv paper.

This repository also contains pre-trained models and implementations for various ASR results including:

The previous iteration of wav2letter (written in Lua) can be found in the wav2letter-lua branch.

Building wav2letter++ and full documentation

All details and documentation can be found on the wiki.

To get started with wav2letter++, checkout the tutorials section.

We also provide complete recipes for WSJ, Timit and Librispeech and they can be found in recipes folder.

Finally, we provide Python bindings for a subset of wav2letter++ (featurization, decoder, and ASG criterion) and a standalone inference framework for running online ASR.


If you use the code in your paper, then please cite it as:

  author          = {Vineel Pratap, Awni Hannun, Qiantong Xu, Jeff Cai, Jacob Kahn, Gabriel Synnaeve, Vitaliy Liptchinsky, Ronan Collobert},
  title           = {wav2letter++: The Fastest Open-source Speech Recognition System},
  journal         = {CoRR},
  volume          = {abs/1812.07625},
  year            = {2018},
  url             = {},

Join the wav2letter community

See the CONTRIBUTING file for how to help out.


wav2letter++ is BSD-licensed, as found in the LICENSE file.

comments powered by Disqus