yeyupiaoling/MASR
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。
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
$ git clone https://github.com/sooftware/conformer.gitPytorch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。
Production First and Production Ready End-to-End Speech Recognition Toolkit
Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.
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
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
End-to-End Automatic Speech Recognition on PyTorch
Data from GitHub · snapshot Sep 24, 2026