The Federal Government of Nigeria has introduced N-ATLAS, a cutting-edge, open-source multilingual and multimodal large language model (LLM) designed to support Yoruba, Hausa, Igbo, and Nigerian-accented English.
Dr. Bosun Tijani, the Minister of Communications, Innovation, and Digital Economy, announced the launch of the AI model on his official X account on Saturday. The unveiling took place during the 80th United Nations General Assembly in New York.
N-ATLAS is created to prioritize African voices in the AI development process, with a special focus on local languages. Dr. Tijani remarked, “By starting with Yoruba, Hausa, Igbo, and Nigerian-accented English, N-ATLAS emphasizes the importance of African voices and diversity in the foundation of AI.”
This initiative marks the first step in a broader plan to position Africa as a key contributor in shaping the future of artificial intelligence.
N-ATLAS is equipped with advanced speech-technology capabilities, including language-specific automatic speech recognition (ASR) models. These models facilitate transcription, improve accessibility, and support local-language applications.
The system can be utilized to create chatbots that help citizens access government services in Yoruba, Hausa, Igbo, and Nigerian-accented English.
Additionally, the ASR models are designed to transcribe radio, TV, and online videos into text, generating captions and subtitles in the four local languages. It can also be used to power call center systems, capture Nigerian-accented speech, and provide automated responses or detect user intent.
Moreover, the model is able to summarize interviews conducted in local languages, enhancing communication and information sharing.
N-ATLAS was developed by the National Centre for Artificial Intelligence and Robotics, in collaboration with Awarri Technologies, as part of Nigeria’s ongoing language-AI initiative. Full documentation of the model is available on Hugging Face.
