Kaldi (software)

From Wikipedia, the free encyclopedia
Jump to: navigation, search
Developer(s) Daniel Povey and others
Stable release Revision 3122 / October 2013; 1 year ago (2013-10)
Written in C++
Operating system Unix systems (GNU/Linux, BSD, OSX 10.{8,9} etc.), Windows (via Cygwin)
Type Speech recognition
License Apache License v.2[1]
Website kaldi.sourceforge.net

Kaldi is a speech recognition toolkit, freely available under the Apache license.

Kaldi aims to provide software that is flexible and extensible.[2] It supports linear transforms, MMI, boosted MMI and MCE discriminative training, feature-space discriminative training, and deep neural networks.[3]

See also[edit]


External links[edit]