jannesg/takalane_afr_roberta

Takalani Sesame 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 the language of Salie - Afrikaans, named after Sesame . The training procedure was pre-processed using standard Huggingface hyperparameters . There are currently 2.8M words in the training code . The data was collected from https://wortschatz.uni-leipzig.de/en Sentences: 2.7M words . The code is based,