https://github.com/dataxujing/asr-paper

:fire: ASR教程: https://dataxujing.github.io/ASR-paper/
https://github.com/dataxujing/asr-paper

asr citrinet conformer contextnet ctc dnn-hmm fbank gmm-hmm jasper las mfcc mocha neural-transducer quartznet rnn-t speech-transformer squeezeformer tandem transformer-transducer wfst

Last synced: about 2 months ago
JSON representation

:fire: ASR教程: https://dataxujing.github.io/ASR-paper/

• Host: GitHub
• URL: https://github.com/dataxujing/asr-paper
• Owner: DataXujing
• License: other
• Created: 2022-11-15T02:03:45.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-01T05:37:22.000Z (7 months ago)
• Last Synced: 2024-07-05T16:50:32.073Z (7 months ago)
• Topics: asr, citrinet, conformer, contextnet, ctc, dnn-hmm, fbank, gmm-hmm, jasper, las, mfcc, mocha, neural-transducer, quartznet, rnn-t, speech-transformer, squeezeformer, tandem, transformer-transducer, wfst
• Homepage:
• Size: 1.07 GB
• Stars: 19
• Watchers: 1
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

        


# Welcome to ASR learning

## GitHub最全ASR教程

**徐静**

2017年开始关注语音识别(ASR)，中间放弃了一段时间，这两年由于Transformer的流行，其端到端的ASR和基于工业应用的开源框架

层出不穷，让我们开始学习吧！

### 目录

- [x] 1.李宏毅ASR课程笔记

- [x] 2.GMM-HMM

- [x] 3.Tandem

- [x] 4.DNN-HMM Hybrid

- [x] 5.LAS

- [x] 6.CTC

- [x] 7.RNA

- [x] 8.RNN-Transducer(RNN-T)

- [x] 9.Neural Transducer

- [x] 10.MoChA]

- [x] 11.Conformer

- [x] 12.Transfomer-Transducer

- [x] 13.DeepSpeech V1,V2,V3

- [x] 14.FSMN

- [x] 15.TDNN

- [x] 16.Quartznet

- [x] 17.Jasper

- [x] 18.Citrinet

- [x] 19.ContextNet 

- [x] 20.WeNet_paper

- [x] 21.WFST

- [x] 22.Hybrid CTC/Attention

- [x] 29.Speech-Transformer

- [x] 30.squeezeformer

- [x] 23.开源语音识别数据集介绍

- [x] 24.Kaldi学习

- ~~25.K2学习~~

- [x] 26.WeNet学习

- [x] 27.ESPNet学习

- [x] 28.NeMo学习

- Triton inference server部署ASR服务(暂时不开源,可提供有偿服务)

- TensorRT ASR模型部署(暂时不开源，可提供有偿服务)

- [x] 31.Paraformer and  FunASR

- [x] 32.Whisper