Conformer 的 PyTorch 非官方实现,把卷积和 Transformer 结合起来做语音识别,适合直接拿来训练或复现 ASR 模型。
开箱即用的语音工具包,覆盖流式语音识别、语音合成、声纹识别、语音翻译和关键词唤醒,自带标点恢复与文本前端,适合快速搭建语音推理服务。
面向生产环境的端到端语音识别工具包,基于 PyTorch 提供 Conformer、Transformer 等模型,可直接训练和部署 ASR 服务。
开源工业级语音识别模型,支持普通话、中文方言和英语,在公开普通话 ASR 榜单上刷新 SOTA,还能精准识别歌词。
基于 PaddlePaddle 的端到端中文语音识别项目,提供 DeepSpeech2、Conformer、Squeezeformer 等主流模型,既有入门案例也有企业级实战方案。
基于 TensorFlow 2 的端到端语音识别框架,支持 Conformer、ContextNet、DeepSpeech2 等模型,可做字符或子词级多语言识别与流式推理。
… --- New Models - hfnet - mobilenet v4 - wav2vec2 conformer --- Removed Models - MiniLM-v2 (w8a8 is removed, floating point still available) --- General Improvements - --
… 2309) - Added GigaSpeech recipes for ASR, with a Conformer RNN-T and WavLM CTC ( 2421) - Overhauled fetch and Pretrained , greatly reducing the use of symlinks out of th
…ormer model. 2755 by @yeyupiaoling Add AMP for U2 conformer. 3167 by @zxcd Mv dataset into paddlespeech.dataset. 3183 3189 by @zh794390558 Fix example/aishell local/train
…, and fix V2 streaming decode issue for efficient conformer @zwglory 1701 Support ort backend in wenetruntime @xingchensong 1708 Support LFMMI @aluminumbox 1725 Support P
…raining by @NevermoreCY in 1600 support efficient conformer by @zwglory in 1636 add blank scale for wfst decoding by @simonwang517 in 1646
- Conformer encoder only - Update README.md (example with CTC loss)