---
title: README
emoji: 👁️
colorFrom: red
colorTo: yellow
sdk: static
pinned: false
---

<img src="https://huggingface.co/spaces/Netra-Lab/README/resolve/main/assets/banner.png" width="100%" alt="Netra Lab: small models for the Khmer language" />

Netra Lab is an independent, non-commercial research lab that focuses on building small-scale models for the Khmer language.

## Models

| Model | What it does | Parameters |
| --- | --- | --- |
| [Netra OCR 1](https://huggingface.co/Netra-Lab/Netra-OCR) | Reads printed Khmer and English text | 19M |
| [Netra MT 1](https://huggingface.co/Netra-Lab/Netra-NMT) | Translates between English and Khmer | 77M |
| [Sota](https://huggingface.co/Darayut/sota-large) · [Sota base](https://huggingface.co/Darayut/sota-base) | Transcribes Khmer and English speech | 204M · 73M |
| [AkaraAlpha](https://github.com/netra-ai-lab/Romanized-Khmer-to-Khmer-Transliteration) | Turns romanized Khmer into Khmer script | 78.7K |

The training corpora and test sets we built for these models are listed below with the datasets.

[Website](https://netra-lab.netlify.app/) · [GitHub](https://github.com/netra-ai-lab) · [Get in touch](https://netra-lab.netlify.app/contact)