julius: A two-pass large vocabulary continuous speech recognition engine¹

Julius is a high-performance large vocabulary continuous speech recognition (LVCSR) engine for speech-related research and development. You can construct your own speech recognition system, but you need a separate English acoustic model and language model or grammar file.

... part of T2, get it here

URL: http://julius.sourceforge.jp/en/julius.html

Author: LEE Akinobu <julius-info [at] lists [dot] sourceforge [dot] jp>
Maintainer: Rene Rebe <rene [at] t2-project [dot] org>

License: BSD
Status: Beta
Version: 4.6

Download: https://github.com/julius-speech/julius/ julius-4.6.tar.gz

T2 source: julius.cache
T2 source: julius.desc

Build time (on reference hardware): 14% (relative to binutils)²

Installed size (on reference hardware): 4.73 MB, 81 files

Dependencies (build time detected): 00-dirtree alsa-lib audiofile bash binutils coreutils diffutils esound findutils gawk grep gzip libsdl2 libsndfile linux-header make pulseaudio readline sed tar zlib

Installed files (on reference hardware): [show]

¹) This page was automatically generated from the T2 package source. Corrections, such as dead links, URL changes or typos need to be performed directly on that source.

²) Compatible with Linux From Scratch's "Standard Build Unit" (SBU).