l3cube-pune/hate-bert-hasoc-marathi

hate-bert-hasoc-marathi

hate-bert-hasoc-marathi is a binary hate speech model fine-tuned on Marathi Hasoc Hate Speech Dataset 2021. The label mappings are 0 -> None, 1 -> Hate.

More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2110.12200)

A new version of Marathi Hate Speech Detection models can be found here:
binary: https://huggingface.co/l3cube-pune/mahahate-bert
multi label: https://huggingface.co/l3cube-pune/mahahate-multi-roberta

@article{velankar2021hate,
  title={Hate and Offensive Speech Detection in Hindi and Marathi},
  author={Velankar, Abhishek and Patil, Hrushikesh and Gore, Amol and Salunke, Shubham and Joshi, Raviraj},
  journal={arXiv preprint arXiv:2110.12200},
  year={2021}
}