Skip to content
This repository has been archived by the owner on Mar 27, 2023. It is now read-only.

Mddct/neural-lm-deprecated

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

82 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

(deprecated, will reimplement by jax) under development may not work until whole pipeline done

neural-lm

focus on fusion on speech recognition

Note

When a language model is used wide beam searches often yield incomplete transcripts. With narrow beams, the problem is less visible due to implicit hypothesis pruning.

See if it appears in ctc+lm fusion

TODO

  • adaptive softmax for large voca (because pytorch offical implementation can't work with torchscript)
  • onnx support and torchscript
  • gru
  • rnn tie embedding
  • gru fusion on wenet runtime ctc prefix beam search
  • transformer-xl with cache
  • transformer-xl with cache to fusion
  • mwer training when lm fusion
  • etc

reference

About

focus on fusion on speech recognition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published