---
license: cc-by-4.0
language: hi
---

## HindBERT-Scratch
HindBERT is a Hindi BERT model. It is a base-BERT model trained from scratch on publicly available Hindi monolingual datasets. 
[project link] (https://github.com/l3cube-pune/MarathiNLP)

More details on the dataset, models, and baseline results can be found in our [paper] (<a href='http://dx.doi.org/10.13140/RG.2.2.14606.84809'> link </a>)

The best version of model is shared <a href='https://huggingface.co/l3cube-pune/hindi-bert-v2'> here </a>

```
@article{joshi2022l3cubehind,
author = {Joshi, Raviraj},
year = {2022},
month = {09},
pages = {},
title = {L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages},
doi = {10.13140/RG.2.2.14606.84809}
}
```