The Federal Government has introduced N-ATLAS, an open-source, multilingual, and multimodal large language model supporting Yoruba, Hausa, Igbo, and Nigerian-accented English.
Dr. Bosun Tijani, Minister of Communications, Innovation, and Digital Economy, announced the launch on his X account on Saturday during the 80th United Nations General Assembly in New York. He emphasized that N-ATLAS aims to center African voices in AI development, stating, “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 making Africa a contributor and leader in shaping AI’s future.”
According to its model card, N-ATLAS features a speech-technology suite with language-specific automatic speech recognition (ASR) models, enabling transcription, accessibility, and local-language applications. The model supports building chatbots for government services in Hausa, Igbo, Yoruba, or Nigerian-accented English, transcribing radio, TV, or online videos into text for captions/subtitles, and powering call-center or voice assistant systems to capture and process Nigerian-accented speech for intent detection or automated responses. It can also summarize interviews in local languages.
Developed by the National Centre for Artificial Intelligence and Robotics in collaboration with partners like Awarri Technologies, N-ATLAS is part of Nigeria’s language-AI initiative. The model’s documentation is available on Hugging Face.
