资源分类
》 资源 》算法》kaldi-nn

kaldi-nn

2020-04-07 | |  32 |   0 |   0

kaldi-nn

Extended speech recognition neural network based on Kaldi for reproducible research

Changelog

  1. Add ReLU, SoftHinge to nnet1

  2. Add Pnorm, Maxout to nnet1

  3. Optimize Maxout GPU kernel code (as fast as Pnorm)

  4. Add LSTM w/o projection layer

  5. Add egs/hkust for reproducing the results

  6. Add ReLU result

  7. Add Convolution and Maxpooling components, and test code

  8. Add example for training ConvNet in nnet2

  9. Add LSTM projected component in nnet2

  10. Add per-utterance training binary

  11. Add per-utterance options for egs-operation binaries


上一篇：kaldi-thesis

下一篇：kaldi_kws

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • shih-styletransfer

    shih-styletransfer Code from Style Transfer ...