The Federal Government Ministry of Communications, Innovation, and Digital Economy has unveiled N-ATLAS, an open-source, multilingual and multimodal large language model that supports Yoruba, Hausa, Igbo and Nigerian-accented English.
Minister of Communications, Innovation, and Digital Economy Dr Bosun Tijani, who announced this in a statement on his X account on Saturday, added that the artificial intelligence was launched on the sidelines of the 80th United Nations General Assembly in New York.
The minister, who N-ATLAS is developed to put African voices at the centre of AI development, said “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.”
According to the product description on its model card, N-ATLaS LLM features a speech-technology suite that includes language-specific automatic speech recognition models, which aid in transcription, accessibility, and local-language applications.
It can be used to build chatbots that answer citizen questions about government services in Hausa, Igbo, Yoruba or Nigerian-accented English.
The ASR models can transcribe radio, TV or online videos into text and generate captions/subtitles in the four local languages.
Call-centre and voice assistant support can deploy ASR and LLM pipelines to capture caller speech in Nigerian accents, transcribe it and supply intent detection or automated replies.
The model can also be used to summarise interviews conducted in local languages.
The product was built by the National Centre for Artificial Intelligence and Robotics and partners, including Awarri Technologies, as part of Nigeria’s language-AI initiative.
The model documentation can be accessed on Hugging Face.