Sai5480/monolingual-tokenizer-iso-mai-vocab-128000

Monolingual Tokenizer - Maithili (Vocab 128000)

This is a monolingual tokenizer trained on Maithili text with vocabulary size 128000.

Usage

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("monolingual-tokenizer-iso-mai-vocab-128000")

Files

• mai.model: SentencePiece model file
• mai.vocab: Vocabulary file
• config.json: Tokenizer configuration

Training Details

• Language: Maithili (mai)
• Vocabulary Size: 128000
• Model Type: SentencePiece Unigram