Nigeria has launched an open-source artificial intelligence model that supports Yoruba, Hausa, Igbo and Nigerian-accented English, in a push to embed African languages and diversity into global AI development, the communications minister said on Saturday.
The multilingual large language model, called N-ATLAS, was unveiled on the sidelines of the 80th United Nations General Assembly in New York, Minister of Communications, Innovation and Digital Economy Bosun Tijani said in a statement on social media platform X.
“Starting with Yoruba, Hausa, Igbo and Nigerian-accented English, N-ATLAS places Africa’s voices and diversity at the foundation of AI,” Tijani said. “This is the first step in a broader journey to make Africa a contributor and leader in shaping AI’s future.”
According to its model card, N-ATLAS features a speech-technology suite with automatic speech recognition models tailored to local languages. The tools can transcribe radio, TV or online video into text, generate captions, and support call centres or voice assistants in Nigerian accents.
The system can also power chatbots to answer citizens’ questions on government services in the four languages, and summarise interviews conducted in local dialects.
N-ATLAS was developed by Nigeria’s National Centre for Artificial Intelligence and Robotics in partnership with Awarri Technologies under the country’s language-AI initiative. Its documentation is available on machine learning platform Hugging Face.