metadata
license: apache-2.0
language:
- bn
- hi
This model is a finetuned version of Twitter/twhin-bert-base model in the Bengali and Hindi languages.
The dataset used is a Kaggle Dataset - Modified-hate-speech-bengali-hindi
This model can classify Bengali and Hindi texts into the following 5 classes :-
- defamation
- hate
- non-hate
- violence
- vulgar