flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
Built on the Flashlight machine learning framework, wav2letter++ implements end-to-end ASR with support for multiple architectures including ConvNets, sequence-to-sequence models with time-depth separable convolutions, and lexicon-free recognition. The toolkit includes reproducible recipes for state-of-the-art systems covering supervised, semi-supervised, and self-training approaches with pre-trained models. Development has consolidated into Flashlight's ASR application module for unified maintenance.
6,446 stars.
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。
philipperemy/deep-speaker
Deep Speaker: an End-to-End Neural Speaker Embedding System.
noahchalifour/rnnt-speech-recognition
End-to-end speech recognition using RNN Transducers in Tensorflow 2.0