jannesg/takalane_xho_roberta

The Takalani Sesame project aims to promote the use of South African languages in NLP . It aims to look at techniques for low-resource languages to equalise performance with larger languages around the world . The project is named after the South African version of Sesame Street . It is based on a model that was created by Jannes Germishuys, a South African language expert . The language is Xhosa, the language of South Africa's version of the popular Sesame TV show . The model was created using an open-source version of NLP software . The training procedure was pre-processed using the standard Huggingface hyperparameters . There are no pre,