MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages.

Anri M. Lombard, Simbarashe Mawere, Temi Aina, Ethan Wolff, Sbonelo Gumede, Elan Novick, Francois Meyer, Jan Buys

Browse the full LREC paper archive.