MahaHate-multi-RoBERTa (Marathi Hate speech identification) is a MahaRoBERTa(l3cube-pune/marathi-roberta) model fine-tuned on L3Cube-MahaHate - a Marathi tweet-based hate speech detection dataset. This is a four-class model with labels as hate, offensive, profane, and not. The 2-class model can be found here
@inproceedings{patil2022l3cube,
title={L3Cube-MahaHate: A Tweet-based Marathi Hate Speech Detection Dataset and BERT Models},
author={Patil, Hrushikesh and Velankar, Abhishek and Joshi, Raviraj},
booktitle={Proceedings of the Third Workshop on Threat, Aggression and Cyberbullying (TRAC 2022)},
pages={1--9},
year={2022}
}
