CUED-RNNLM Toolkit

CUED-RNNLM Toolkit

Introduction

CUED-RNNLM toolkit present an implementation of RNNLM training (on GPU), and efficient evaluation(on CPU). We have recently release CUED-RNNLM v1.0, which support LSTM, GRU, Highway structure, as well as more flexible deep structure.

Lattice rescoring and other functions will be updated soon, please feel free to send me email (xc257@cam.ac.uk) if you need it for you current project.

We strongly recommend you to use CUED-RNNLM v1.0, and the old version (CUED-RNNLM v0.1) won't be maintained and update

CUED-RNNLM.v1.0 - CUED-RNNLM.v0.1 - Highlights - Document - Recipe - Usage - Contact - Reference - License

CUED-RNNLM v1.0

cued-rnnlm v1.0

cued-rnnlm v1.0 evalation on CPU

CUED RNNLM Toolkit Document v1.0

Recipe for training and evaluation (PPL and N-best rescoring)

Highlights

CUED-RNNLM v0.1

cued-rnnlm v0.1 (both linux and windows supported)

cued-rnnlm v0.1a (modify gradient clipping for NCE training with shared noise sample(under testing))

tools to evaluate cued-rnnlm on CPU

HTK 3.4.1 patch(RNNLM latrescore supported in HLRescore) HTKLib change file list HTKTools change file list

Example of RNNLM lattice rescore

Kaldi lattice to HTK lattice Convert Tools HTK and Kaidi Lattices

External Link

HTK 3.5 supports RNNLMs generated by CUED-RNNLM toolkit for lattice rescoring now!

Highlights

Document

CUED RNNLM Toolkit

AMI Data and Recipe

Recipe

Log file for Google 1 Billion Corpus

log file

Usage

rnnlm is invoked by typing the commend line

Contact

Xie Chen - xc257 at cam.ac.uk

References

Acknowledgement

This work is supported by Toshiba Research Europe Ltd, Cambridge Research Lab. It was also supported by EPSRC grant EP/I031022/1 (Natural Speech Technology).

We would like to thank Andreas Stolcke for porting it into windows (MS Visual C) and valuable advices.

License

This toolkit is freely available under the BSD license and copyright from the RNNLM toolkit.