---
language:
- "th"
tags:
- "thai"
- "masked-lm"
base_model: clicknext/phayathaibert
license: "apache-2.0"
pipeline_tag: "fill-mask"
mask_token: "<mask>"
---

# camembert-thai-base

## Model Description

This is a CamemBERT model pre-trained on Thai texts, derived from [PhayaThaiBERT](https://huggingface.co/clicknext/phayathaibert) with the tokenizer refined. You can fine-tune `camembert-thai-base` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/camembert-thai-base-upos), [dependency-parsing](https://huggingface.co/KoichiYasuoka/camembert-thai-base-ud-goeswith), and so on.

## How to Use

```py
from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/camembert-thai-base")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/camembert-thai-base")
```