Home› Projects› wav2letter
wav2letter
C++

wav2letter

Facebook AI Research's Automatic Speech Recognition Toolkit

by flashlight · GitHub
6.4k
Stars
991
Forks
2017
Created
1 mo ago
Last commit
cpp
Category
C++
Language
cppdeep-learningend-to-endC++
View on GitHub
In plain words

Recognize speech automatically using a toolkit designed for building speech recognition systems.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
wav2letter — GitHub preview card
📈 Star history
6 4426 440
2026-07-042026-08-31
📈 Track wav2letter

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Facebook AI Research's Automatic Speech Recognition Toolkit

wav2letter has 6.4k stars on GitHub. It has been forked 991 times. wav2letter is written mainly in C++. It has been in active development since 2017. Its main topics are cpp, deep-learning, end-to-end, speech-recognition.

❓ Frequently asked questions

What is wav2letter?

Facebook AI Research's Automatic Speech Recognition Toolkit

Is wav2letter open source?

wav2letter is an open-source project.

Is wav2letter free?

Yes. wav2letter is free and open source — you can use, modify and self-host it.

What language is wav2letter written in?

wav2letter is written mainly in C++.

🏅 Maintainer of this project?
olud.ai badge — wav2letter

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=flashlight-wav2letter)](https://olud.ai/project/flashlight-wav2letter.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
VAD
[ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
★ 1.3k · autonomous-driving
sharesend-to-end
kaldi-gstreamer-server
Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer f…
★ 1.1k · speech-recognition
sharesspeech-recognition
FastASR
这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数…
★ 553 · speech-recognition
sharesspeech-recognition
Senna
Bridging Large Vision-Language Models and End-to-End Autonomous Driving
★ 551 · autonomous-driving
sharesend-to-end
dragonfly
Speech recognition framework allowing powerful Python-based scripting and extension of Dragon N…
★ 413 · python
sharesspeech-recognition
LaneDetection_End2End
End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)
★ 663 · computer-vision
sharesend-to-end
deepvoice3_pytorch
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
★ 2k · end-to-end
sharesend-to-end
DiffPhysDrone
Published on Nature Machine Intelligence! The first real robot(quadrotor) based on differentiab…
★ 581 · drone
sharesend-to-end
end2end-asr-pytorch
End-to-End Automatic Speech Recognition on PyTorch
★ 304 · asr
sharesend-to-end
espnet
End-to-End Speech Processing Toolkit
★ 9.9k · chainer
sharesend-to-end

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.