This script is for Slackware 14.2 only and may be outdated.

SlackBuilds Repository

14.2 > Development > julius (4.3.1)

"Julius" is a high-performance, two-pass large vocabulary continuous
speech recognition (LVCSR) decoder software for speech-related
researchers and developers. Based on word N-gram and context-dependent
HMM, it can perform almost real-time decoding on most current
PCs in 60k word dictation task. Major search techniques are fully
incorporated such as tree lexicon, N-gram factoring, cross-word context
dependency handling, enveloped beam search, Gaussian pruning, Gaussian
selection, etc. Besides search efficiency, it is also modularized
carefully to be independent from model structures, and various HMM
types are supported such as shared-state triphones and tied-mixture
models, with any number of mixtures, states, or phones. Standard
formats are adopted to cope with other free modeling toolkit such as
HTK, CMU-Cam SLM toolkit, etc.

Maintained by: Roberto Metere
Keywords: julius,speech,recognition,LVCSR,decoder,voice
ChangeLog: julius


Source Downloads:
julius-4.3.1.tar.gz (7868d89ac1fa729f477a7c700efaf087)

Download SlackBuild:
julius.tar.gz.asc (FAQ)

(the SlackBuild does not include the source)

Individual Files:

Validated for Slackware 14.2

See our HOWTO for instructions on how to use the contents of this repository.

Access to the repository is available via:
ftp git cgit http rsync

© 2006-2024 Project. All rights reserved.
Slackware® is a registered trademark of Patrick Volkerding
Linux® is a registered trademark of Linus Torvalds