Renaissance Labs

Atlas / Africa

Community collective · Accra, Ghana

Ghana NLP

An open-source community building language technology for Ghanaian languages such as Twi, Ewe and Frafra.

low-resource languageslanguage modelsdatasetsmachine translation

Accra, Ghana

Type
Community collective
Based in
Accra, Ghana
Key papers
1
Featured projects
8

About

Ghana NLP is an open-source initiative working on natural language processing for Ghanaian languages and its application to local problems. It aims to build better training data, adapt state-of-the-art techniques to low-resource settings and create working systems such as translators.

Its projects include the Khaya Translator apps, Ghana Speech ID, the Nsanku translation and ASR benchmarks, and ABENA. The community reports about 600 members and invites volunteers through a join form.

Mission and ambitions

The initiative works to bring Ghanaian languages into modern language technology, beginning with Twi and extending to others.

Known for

  1. 01

    Khaya translation apps

  2. 02

    Twi language resources

  3. 03

    Nsanku benchmarks

Milestones

  1. 2020

    ABENA

    Introduced a BERT-based language model for Twi.

  2. 2026

    ghana-speech dataset

    Released 2,247 hours of speech across 42 Ghanaian languages, followed by a phoneme ASR model.

Open source

GitHubgithub.com/GhanaNLP

Research papers

Notable releases

Openness

Models and datasets are published on Hugging Face and code on GitHub; licences differ per resource.

People

  • Paul AzunreCo-founder

    Described as co-founder of Ghana NLP in press coverage.

Listed from the lab's own pages and public profiles.

Contact and community

Contact details and links are on the lab's website (https://ghananlp.org); code questions go through issues on their GitHub organisation.

Sources

Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.

Labs nearby