metadata

license: apache-2.0
language:
  - ar
tags:
  - Aranizer
  - Arabic Tokenizer
  - PBE
  - AutoTokenizer

Aranizer | Arabic Tokenizer

Aranizer is an Arabic PBE-based tokenizer designed for efficient and versatile tokenization.

Features

Tokenizer Name: Aranizer
Type: PBE tokenizer
Vocabulary Size: 64,000
Total Number of Tokens: 1,358,099
Fertility Score: 1.764
It supports Arabic Diacritization

Aranizer Collection Achieved State of the Art Arabic Tokenizer

The Aranizer tokenizer has achieved state-of-the-art results on the Arabic Tokenizers Leaderboard on Hugging Face. Below is a screenshot highlighting this achievement:

Screenshot showing the Aranizer Tokenizer achieving state of the art

How to Use the Aranizer Tokenizer

The Aranizer tokenizer can be easily loaded using the transformers library from Hugging Face. Below is an example of how to load and use the tokenizer in your Python project:

from transformers import AutoTokenizer

# Load the Aranizer tokenizer
tokenizer = AutoTokenizer.from_pretrained("riotu-lab/Aranizer-PBE-64k")

# Example usage
text = "اكتب النص العربي"
tokens = tokenizer.tokenize(text)
token_ids = tokenizer.convert_tokens_to_ids(tokens)

print("Tokens:", tokens)
print("Token IDs:", token_ids)

## Citation

@article{koubaa2024arabiangpt,
  title={ArabianGPT: Native Arabic GPT-based Large Language Model},
  author={Koubaa, Anis and Ammar, Adel and Ghouti, Lahouari and Necar, Omer and Sibaee, Serry},
  year={2024},
  publisher={Preprints}
}