GiellaLT provides an infrastructure for rule-based language technology aimed at minority and indigenous languages, and streamlines building anything from keyboards to speech technology.

View GiellaLT on GitHub

Page Content

GiellaLT language models

Beware that the documentation pages for most Experimental repos have little or no content, and that documentation for other languages probably is out-of-date. Writing documentation for each language repository is an ongoing effort, and part of the development process.

The languages are grouped in three different ways, according to maturity, geography and language family. Private repositories are not listed.

Grouped according to maturity of the resources

The maturity levels are production, beta, alpha and experimental. Some of the beta language models are used in practical applications.

Being in the Production group does not necessarily mean a language model is in production for all purposes, it could be for one only. See the documentation for each language for further details.

Maturity: Production Production language resources

Maturity: Beta Beta language resources

Maturity: Alpha Alpha language resources

Maturity: Experiment Experimental language resources

Maturity: Undefined Language resources of undefined maturity

Grouped according to geography

Languages of the Nordic countries

Languages of Russia

Other European languages

Languages in North America

Languages in Africa

Languages in other parts of the world

Languages with no geography tag

Grouped according to language family

Uralic Languages

Eskimo-Aleut Languages

Algic Languages

Indoeuropean languages

Niger-Congo Languages

Turkic Languages

Languages of other language families, isolates, artificial languages

Languages with no language family tag