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
Downloads last month
12
Safetensors
Model size
279M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.