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 researches.
Releasing complete recipes is an important goal of Kaldi.
The code is publicly available under a license that permits odifications and re-release, the code is encouraged to release along with script directories.
The Kaldi can be downloaded by typing into a shell:
git clone
--origin upstream
cd kaldi
If you want to get updates and bug fixes, you can go to some checked-out directory, and type
git pull
The top-level installation instructions are in the file INSTALL.
For Windows, there are separate instructions in windows/INSTALL.
See also the build process (how Kaldi is compiled) which explains how the build works internally.
The example scripts are in legs.
[0]