Sai5480/monolingual-tokenizer-native-tel-vocab-128000

Monolingual Tokenizer - Telugu (Vocab 128000)

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

Usage

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("monolingual-tokenizer-native-tel-vocab-128000")

Files

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

Training Details

• Language: Telugu (tel)
• Vocabulary Size: 128000
• Model Type: SentencePiece Unigram