Despite being spoken by over 70 million people, Hausa remains underrepresented in current NLP research and applications. This project aims to address this disparity by creating resources that can be used in practical applications and further research.

Objectives

• Develop pre-trained language models for Hausa
• Fine-tune models for specific NLP tasks
• Improve accessibility of NLP tools for the Hausa-speaking community
• Bridge the technological gap for low-resource languages

Tasks

Models developed for this project aim to tackle various NLP/Vision tasks, including but not limited to:

• Text generation
• Machine translation
• Vision question answering