pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
2.37k
stars
446
forks
source link
Add support for GAN front-end training and evaluation #258
Summary
Support is added to train a Guided-GAN front-end and use it to improve the performance of a trained acoustic model. The updates include: