Need help with pychain?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

YiwenShaoStephen
199 Stars 42 Forks 18 Commits 2 Opened issues

Description

PyTorch implementation of LF-MMI for End-to-end ASR

Services available

!
?

Need anything else?

Contributors list

# 91,716
Perl
Shell
c-plus-...
adversa...
10 commits
# 16,644
Shell
opencl
pytorch
kaldi
7 commits
# 50,777
Shell
c-plus-...
ml
automat...
1 commit

PyTorch implementation of LF-MMI for End-to-end ASR

End-to-end version of lattice-free MMI (LF-MMI or chain model) implemented in PyTorch.
TODO: regular version of LF-MMI.

What's New:

  • August 2020: GPU computation for graphs in log domain (recommended for numerator graphs)
  • April 2020: Support unequal length sequences within a minibatch
  • April 2020: Examples of using PyChain: Espresso and pychain-example
  • January 2020: GPU computation for both denominator and numerator graphs

Installation and Requirements

First-time Installation (including OpenFST)

pip install kaldi_io
git clone https://github.com/YiwenShaoStephen/pychain.git
cd pychain
make

Update

Whenever you update or modify any none-python codes (e.g. .c or .cu) in pychain, you need to re-compile it by

make pychain

Reference

"PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR", Yiwen Shao, Yiming Wang, Daniel Povey and Sanjeev Khudanpur (pdf)

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.