---
language: mr
license: cc-by-4.0
datasets:
- L3Cube-MahaHate
widget:
- text: "I like you. </s></s> I love you."
---


## MahaHate-multi-RoBERTa

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 <a href='https://huggingface.co/l3cube-pune/mahahate-bert'> here </a>

[dataset link] (https://github.com/l3cube-pune/MarathiNLP)

More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2203.13778)

```
@article{velankar2022l3cube,
  title={L3Cube-MahaHate: A Tweet-based Marathi Hate Speech Detection Dataset and BERT models},
  author={Velankar, Abhishek and Patil, Hrushikesh and Gore, Amol and Salunke, Shubham and Joshi, Raviraj},
  journal={arXiv preprint arXiv:2203.13778},
  year={2022}
}
```