AI for the Nepali language.
Open datasets, models, and tools for 17 million speakers. Built in the open under CC BY 4.0 and Apache 2.0. Project Bhasa is Suswo's commitment to low-resource language AI.
Three phases. Long game.
Open Contributor
Open community. Datasets and models published freely on Hugging Face and GitHub under CC BY 4.0 and Apache 2.0.
Open Core
Free base models with a hosted API. Developers call the API for free at limited rate — pay for production scale.
FUTURECommercial Products
Nepali speech-to-text, translation API, writing assistant, and government / NGO contracts.
FUTUREOpen datasets.
Datasets publishing soon.
Phase 1 is underway. The first dataset will appear here and on Hugging Face when it passes our quality review.
Watch on Hugging Face ↗Models we've trained.
Models publishing soon.
We train on the published datasets. The first checkpoint will release alongside or shortly after the first dataset.
How to contribute.
Native speakers
Review and validate data — no ML experience needed. If you speak Nepali, you can help.
Contributor guide →Engineers
Open PRs — dataset pipelines, evaluation scripts, and NLP tooling. We use Python and Hugging Face Transformers.
View repos →Linguists
Help curate and annotate data correctly. Linguistic expertise ensures our datasets are actually useful.
Get involved →Help us build AI in Nepali.
Every dataset row, every commit, every share helps build the future of Nepali AI. Open source, open data, open research.