Skip to content

端到端语音识别实现;包含LAS、CTC、RNNT解码方式,模型SA(MHA)、LSTM、CNN、DFSMN等

Notifications You must be signed in to change notification settings

whull/end2end_ASR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

end2end_ASR

端到端语音识别系统 已完成LAS(基于LSTM-LSTM模型)

Requirements

  • Python 3.6
  • Tensorflow 1.6+: pip install tensorflow==1.6.0
  • librosa

About

端到端语音识别实现;包含LAS、CTC、RNNT解码方式,模型SA(MHA)、LSTM、CNN、DFSMN等

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages