About this project
This repository contains finite state source files for the Finnish language, used for building morphological analysers, proofing tools, and dictionaries. It is part of the GiellaLT open-source multi-lingual infrastructure project and is licensed under GPLv3.
Key components include finite state transducer (FST) source files for Finnish morphology, Constraint Grammar (VislCG3) based analysis tools, and spell checking files for both desktop and mobile platforms. Nightly and CI/CD installation packages are available for Windows, macOS, and mobile devices, though these are not tested for language quality and may contain regressions.
The project requires an FST compiler (HFST, Foma, or Xerox Xfst) and VislCG3 Constraint Grammar tools. Installation can be done through the Divvun Installer or via the standard GNU build system (autogen.sh, configure, make, make install). Downloadable speller files (.bhfst) can be tested with divvunspell, with separate files for desktop and mobile due to different error models.
Documentation is available for both language-specific and general usage. The project has been published in academic literature (LREC 2022) and includes citation information for researchers. The authors are available to grant alternative licensing choices upon request.
Comments
0 Rating appears after 10 ratings
Sign in to join the discussion.