Production First and Production Ready End-to-End Speech Recognition Toolkit
$ git clone https://github.com/wenet-e2e/wenet.gitOpen-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
🔉 Youtube Videos Transcription with OpenAI's Whisper
Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.
End-to-End Automatic Speech Recognition on PyTorch
Data from GitHub · snapshot Sep 24, 2026