8000 GitHub - cweng6/kaldi-lstm: C++ implementation of LSTM (Long Short Term Memory), in Kaldi's nnet1 framework. Used for automatic speech recognition, possibly language modeling etc, the training can be switched between CPU and GPU(CUDA).
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
/ kaldi-lstm Public
forked from dophist/kaldi-lstm

C++ implementation of LSTM (Long Short Term Memory), in Kaldi's nnet1 framework. Used for automatic speech recognition, possibly language modeling etc, the training can be switched between CPU and GPU(CUDA).

0 stars 96 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

cweng6/kaldi-lstm

BranchesTags
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

63 Commits
google
google
 
 
misc
misc
 
 
standard
standard
 
 
README.md
README.md
 
 

Repository files navigation

LSTM-projected BPTT in Kaldi nnet1

Diagram

Diagram

Notes:

  • peephole connection(purple) are diagonal
  • output-gate peephole is not recursive
  • dashed arrows: adaptive weight, i.e activations of (input gate, forget gate, output gate)

Currently implementation includes two versions:

  • standard
  • google

Go to sub-directory to get more details.

About

C++ implementation of LSTM (Long Short Term Memory), in Kaldi's nnet1 framework. Used for automatic speech recognition, possibly language modeling etc, the training can be switched between CPU and GPU(CUDA).

Resources

Readme
Activity

Stars

0 stars

Watchers

1 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages

  • C++ 97.4%
  • Other 2.6%
0