Bangla Bert

🚀 Bangla BERT Base

We have published a pre - trained Bangla BERT language model named bangla - bert, which is now available on the Hugging Face model hub. This model is based on the mask language modeling described in BERT and the GitHub [repository](https://github.com/google - research/bert).

✨ Features

• Tags: Bert base Bangla, Bengali Bert, Bengali lm, Bangla Base Bert, Bangla Bert language model, Bangla Bert
• Datasets: BanglaLM dataset

📦 Installation

The model is available on the Hugging Face model hub. You can directly use it through the Hugging Face transformers library as shown in the usage examples below.

💻 Usage Examples

Basic Usage

bangla - bert Tokenizer

from transformers import AutoTokenizer, AutoModel
bnbert_tokenizer = AutoTokenizer.from_pretrained("Kowsher/bangla-bert")
text = "খাঁটি সোনার চাইতে খাঁটি আমার দেশের মাটি"
bnbert_tokenizer.tokenize(text)
# output: ['খাটি', 'সে', '##ানার', 'চাইতে', 'খাটি', 'আমার', 'দেশের', 'মাটি']

Advanced Usage

MASK Generation Here, we can use the Bangla BERT base model for masked language modeling:

from transformers import BertForMaskedLM, BertTokenizer, pipeline
model = BertForMaskedLM.from_pretrained("Kowsher/bangla-bert")
tokenizer = BertTokenizer.from_pretrained("Kowsher/bangla-bert")

nlp = pipeline('fill-mask', model=model, tokenizer=tokenizer)
for pred in nlp(f"আমি বাংলার গান {nlp.tokenizer.mask_token}"):
  print(pred)
# {'sequence': 'আমি বাংলার গান লিখি', 'score': 0.17955434322357178, 'token': 24749, 'token_str': 'লিখি'}


nlp = pipeline('fill-mask', model=model, tokenizer=tokenizer)
for pred in nlp(f"তুই রাজাকার তুই {nlp.tokenizer.mask_token}"):
  print(pred)
# {'sequence': 'তুই রাজাকার তুই রাজাকার', 'score': 0.9975168704986572, 'token': 13401, 'token_str': 'রাজাকার'}


nlp = pipeline('fill-mask', model=model, tokenizer=tokenizer)
for pred in nlp(f"বাংলা আমার {nlp.tokenizer.mask_token}"):
  print(pred)
# {'sequence': 'বাংলা আমার অহংকার', 'score': 0.5679506063461304, 'token': 19009, 'token_str': 'অহংকার'}  

📚 Documentation

Corpus Details

We trained the Bangla BERT language model using the BanglaLM dataset from Kaggle BanglaLM. There are 3 versions of the dataset, which is approximately 40GB. After downloading the dataset, we proceeded with masked language modeling.

📄 License

No license information is provided in the original document.

📚 Citation

M. Kowsher, A. A. Sami, N. J. Prottasha, M. S. Arefin, P. K. Dhar and T. Koshiba, "Bangla - BERT: Transformer - based Efficient Model for Transfer Learning and Language Understanding," in IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3197662.

👨‍💻 Author

Kowsher