Sai5480's picture
Add README for guj tokenizer
62b9027 verified
---
license: mit
tags:
- tokenizer
- sentencepiece
- monolingual
- guj
- vocab-128000
---
# Monolingual Tokenizer - Gujarati (Vocab 128000)
This is a monolingual tokenizer trained on Gujarati text with vocabulary size 128000.
## Usage
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("monolingual-tokenizer-iso-guj-vocab-128000")
```
## Files
- `guj.model`: SentencePiece model file
- `guj.vocab`: Vocabulary file
- `config.json`: Tokenizer configuration
## Training Details
- Language: Gujarati (guj)
- Vocabulary Size: 128000
- Model Type: SentencePiece Unigram