Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models
Published in ArXiv preprint, 2020
Recommended citation: Madikeri, S., Tong, S., Zuluaga-Gomez, J., Vyas, A., Motlicek, P. and Bourlard, H., 2020. Pkwrap: a pytorch package for lf-mmi training of acoustic models. arXiv preprint arXiv:2010.03466. https://arxiv.org/abs/2010.03466
We present a simple wrapper that is useful to train acoustic models in PyTorch using Kaldi’s LF-MMI training framework. The wrapper, called pkwrap (short form of PyTorch kaldi wrapper), enables the user to utilize the flexibility provided by PyTorch in designing model architectures. It exposes the LF-MMI cost function as an autograd function. Other capabilities of Kaldi have also been ported to PyTorch. This includes the parallel training ability when multi-GPU environments are unavailable and decode with graphs created in Kaldi. The package is available on Github at this URL (Pkwrap package).
Recommended citation:
Madikeri, S., Tong, S., Zuluaga-Gomez, J., Vyas, A., Motlicek, P. and Bourlard, H., 2020. Pkwrap: a pytorch package for lf-mmi training of acoustic models. arXiv preprint arXiv:2010.03466.
- BibTeX:
@article{madikeri2020pkwrap,
title={Pkwrap: a pytorch package for lf-mmi training of acoustic models},
author={Madikeri, Srikanth and Tong, Sibo and Zuluaga-Gomez, Juan and Vyas, Apoorv and Motlicek, Petr and Bourlard, Herv{\'e}},
journal={arXiv preprint arXiv:2010.03466},
year={2020}
}