metadata
title: README
emoji: 👁️
colorFrom: red
colorTo: yellow
sdk: static
pinned: false
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 | Reads printed Khmer and English text | 19M |
| Netra MT 1 | Translates between English and Khmer | 77M |
| Sota · Sota base | Transcribes Khmer and English speech | 204M · 73M |
| AkaraAlpha | 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.