| license: mit | |
| # Bangla FastText Model | |
| This is a FastText pre-trained model for the Bengali language | |
| This model is build for [bnlp](https://github.com/sagorbrur/bnlp) package. | |
| ## Datasets | |
| - [Wikipedia dump datasets](https://dumps.wikimedia.org/bnwiki/latest/) | |
| ## Training Details | |
| - Fasttext trained with total words = 20M, vocab size = 1171011, epoch=50, embedding dimension = 300 | |
| ## Evaluation Details | |
| - training loss = 0.318668 |