flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
This is an automatic speech recognition toolkit that helps researchers and developers convert spoken audio into text. It takes audio recordings as input and produces transcribed text. This tool is primarily used by AI/ML researchers and engineers working on speech technology.
6,446 stars.
Use this if you are a researcher developing or experimenting with state-of-the-art automatic speech recognition models, especially for academic reproduction or advancement.
Not ideal if you are a non-developer seeking a ready-to-use application for transcribing audio without needing to build or customize models.
Stars
6,446
Forks
997
Language
C++
License
—
Category
Last pushed
Jan 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/flashlight/wav2letter"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
espnet/espnet
End-to-End Speech Processing Toolkit
yeyupiaoling/PPASR
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
yeyupiaoling/PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
pannous/tensorflow-speech-recognition
🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks
google/uis-rnn
This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN)...