---
library_name: transformers
tags: []
---

XLM Roberta Tokenizer trained with 162M tokens of Khmer text.

```python
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("seanghay/xlm-roberta-khmer-32k-tokenizer")
tokenizer.tokenize("សួស្ដីកម្ពុជា!")
```