50  Last view: 2021-07-31

Language model prim-5.0-sane

http://korpus.sk/prim(2d)5(2e)0(2f)models.html

This is a language model from the Slovak National Corpus. This model is a 733 million token collection. Language model is in the iARPA format, using witten-bell smoothing. It was created by the IRSTLM Tooklit. It is lowercased. The model has been released with the contribution of the EuroMatrixPlus project.