metadata
language:
- bn
- hi
- hi-en
- ka-en
- ma-en
- mr
- ta-en
- ur
- ur-en
- en
license: afl-3.0
This model is used detecting abusive speech in Bengali, Devanagari Hindi, Code-mixed Hindi, Code-mixed Kannada, Code-mixed Malayalam, Marathi, Code-mixed Tamil, Urdu, Code-mixed Urdu, and English languages. The allInOne in the name refers to the Joint training/Cross-lingual training, where the model is trained using all the languages data. It is finetuned on MuRIL model. The model is trained with learning rates of 2e-5. Training code can be found at this url
For more details about our paper
Coming soon
Please cite our paper in any published work that uses any of these resources.
Coming soon