---
license: mit
tags:
- tokenizer
- sentencepiece
- monolingual
- ori
- vocab-128000
---

# Monolingual Tokenizer - Odia (Vocab 128000)

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

## Usage

```python
from transformers import AutoTokenizer

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

## Files

- `ori.model`: SentencePiece model file
- `ori.vocab`: Vocabulary file
- `config.json`: Tokenizer configuration

## Training Details

- Language: Odia (ori)
- Vocabulary Size: 128000
- Model Type: SentencePiece Unigram