Netra Lab is an independent, non-commercial research lab. We build small models that read, hear, translate and write Khmer, and every one is free to download, test and build on.
Build AI that works in Khmer, runs on ordinary devices, and is free for anyone to use, check and improve
Every model, dataset and line of code is published
You don't need an account, API key or credit card to use anything we make. Code, weights and reports are released under licences that allow commercial use, changes and redistribution. We won't lock the work away later.
Code
GitHubWeights
Hugging FaceWrite-up
ResearchEvery model comes with a written report
Each report covers how the model was trained, what it was measured against and the test data we used. We publish the failures alongside the scores.
Run by one researcher, not a company
No one with a stake in the results funds the lab. Anyone can build on our work, and we want people to train better models on top of it.
Every model is designed around how Khmer is written and spoken
More than 16 million people speak Khmer, and most AI tools barely understand it. Public training data is thin and test sets barely exist.
Khmer script breaks tools made for the Latin alphabet: consonants stack, vowels attach around them, and words run together without spaces.
Models are sized for an ordinary laptop or phone
We keep models small enough to run on the hardware people in Cambodia have, without a rented server.