Speech Recognition
lhotse-speech/lhotse🔥 active
Tools for handling multimodal data in machine learning projects.
PythonApache-2.0updated Sep 22, 2026
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
$ git clone https://github.com/xinjli/allosaurus.gitTools for handling multimodal data in machine learning projects.
[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。
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
UniSpeech - Large Scale Self-Supervised Learning for Speech
End-to-End Automatic Speech Recognition on PyTorch
Data from GitHub · snapshot Sep 24, 2026