Upstream software project

julius

Large vocabulary continuous speech recognition (LVCSR) decoder software

About julius

Large vocabulary continuous speech recognition (LVCSR) decoder software

This project links 6 native package records across 2 recorded operating-system releases. Compare the retained versions and architectures below, then open the package for your own release.

These are catalog observations, not a guarantee of installation, compatibility, or upstream support.

Project pictures and package coverage

julius repository preview from GitHub
Project repository preview, supplied by GitHub. Open source repository
Fedora 43: 3 package records; Fedora 44: 3 package records. Catalog coverage diagram, not an application screenshot.julius: recorded package coverageFedora 433 recordsFedora 443 records
OpenFactory diagram of linked package records. It is not an application screenshot.

Project identity

Project
julius
Publisher
Not authoritatively mapped
Native package records
6
Operating systems
fedora-43, fedora-44
License expression
BSD-3-Clause AND MIT
Source repository
Open source repository

Source-reported description

The fullest retained description is shown with its source. Distribution packaging descriptions may include downstream details.

"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.

Description source

Packages by operating system

Compare recorded versions, then open a package for dependency, file, checksum, and repository evidence. Version strings are distribution-specific, not a ranking of newer software.

Fedora 43

  1. Package julius

    43 (Fedora 43) (Unspecified): Large vocabulary continuous speech recognition (LVCSR) decoder software

    4.6-9.fc43: aarch64 i686 x86_64

    Source: julius

  2. Package julius-devel

    43 (Fedora 43) (Unspecified): Development files and libraries for libjulius and libsent

    4.6-9.fc43: aarch64 i686 x86_64

    Source: julius

  3. Package julius-japanese-models

    43 (Fedora 43) (Unspecified): Julius Japanese language model and acoustic models

    4.6-9.fc43: noarch

    Source: julius

Fedora 44

  1. Package julius

    44 (Fedora 44) (Unspecified): Large vocabulary continuous speech recognition (LVCSR) decoder software

    4.6-11.fc44: aarch64 i686 x86_64

    Source: julius

  2. Package julius-devel

    44 (Fedora 44) (Unspecified): Development files and libraries for libjulius and libsent

    4.6-11.fc44: aarch64 i686 x86_64

    Source: julius

  3. Package julius-japanese-models

    44 (Fedora 44) (Unspecified): Julius Japanese language model and acoustic models

    4.6-11.fc44: noarch

    Source: julius

Project resources and further reading

Mapping provenance

Only source-backed identity signals create public cross-OS links. A reviewer can later approve or dispute an inferred relationship without rewriting native package history.

No field-level source record is published yet.