Kaldi 2016

From HPC users
Revision as of 11:34, 21 July 2021 by Schwietzer (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigationJump to search


Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers. 1

Installed version(s)

The following versions are installed and currently available...

... on environment hpc-env/8.3:

  • Kaldi/5.5-fosscuda-2019b_2021.07

Loading / Using Kaldi

To load the desired version of the module, use the module load command, e.g.

module load hpc-env/8.3
module load Kaldi 

Always remember: this command is case sensitive!

If you need some advice on how to get started with Kaldi, you could visit their documentation page and start here at the section Your first task and then continue with Data preparation and so on.
Since Kaldi does not have that one executable to work with (the bin dir counts > 500 executables!), it seemed better to refer to the external official documentation than to go through every step of any possible use case in this wiki.


The full documentation can be found here.