Nigeria has launched N-ATLAS, an open source multilingual AI model, to embed African voices in global AI and drive digital inclusion.
Nigeria has taken a landmark step in artificial intelligence with the launch of N-ATLAS, an open-source, multilingual, and multimodal large language model (LLM) capable of processing Yoruba, Hausa, Igbo, and Nigerian-accented English. The announcement was made by Dr Bosun Tijani, Minister of Communications, Innovation and Digital Economy, during the sidelines of the 80th United Nations General Assembly (UNGA80) in New York.
Dr Tijani stated, “We just released N-ATLAS v1 — Nigeria’s open source, multilingual & multimodal Large Language Model — on the sidelines of #UNGA80 in New York. Starting with Yoruba, Hausa, Igbo and Nigerian-accented English, N-ATLAS places Africa’s voices and diversity at the foundation of AI. This is the first step in a broader journey to make Africa a contributor and leader in shaping AI’s future.”
The project was developed by the National Centre for Artificial Intelligence and Robotics in partnership with Awarri Technologies as part of Nigeria’s language-AI initiative, designed to advance indigenous language technologies and promote digital inclusion.
From a technical standpoint, N-ATLAS features a state-of-the-art automatic speech recognition system for major Nigerian languages and is fine-tuned on the Whisper Small architecture. Its language model, N-ATLaS-LLM, is built on Llama-3 8B, trained on more than 400 million tokens of multilingual instruction data. The model demonstrates strong performance across African languages while maintaining high accuracy in English.
Nigeria’s unveiling of N-ATLAS at UNGA80, where Vice President Kashim Shettima is leading the national delegation, underscores the country’s ambition to position Africa as a key player in the global AI landscape while commemorating the 80th anniversary of the United Nations.
