Search everything

SabiYarn-125M is a 125M-parameter decoder-only foundation model pretrained on Nigerian-language text, the first in the SabiYarn series. It supports English, Yoruba, Hausa, Igbo and Nigerian Pidgin plus Fulfulde, Efik and Urhobo, with fine-tuned variants for translation, NER, sentiment and diacritization. It was built by Aletheia.ai Research Lab and presented at the AfricaNLP 2025 workshop.

[ingest-scout] Open-source African speech AI ecosystem from UBC's Deep Learning & NLP Lab: 5 ASR models covering 43 languages, 7 TTS models covering 7 languages, spoken language identification for 49 languages, and SimbaBench evaluation dataset. Introduced at EMNLP 2025 (paper: 'Voice of a Continent'); models hosted on HuggingFace under UBC-NLP. Confirmed live at github.com/UBC-NLP/simba with CC-BY-4.0 license. Distinct from african-whisper (ASR only), bibletts (TTS only), and spitch (commercial) already in registry.

Imported from a community submission, needs review.

Sunflower-14B is a Qwen3-14B based multilingual LLM by Sunbird AI supporting translation and text generation across 31 Ugandan languages plus English. It achieves the highest translation accuracy in 24 of 31 evaluated language pairs and targets healthcare, agriculture, education and government use cases. It is released under Apache 2.0 with quantized GGUF and W8A8 variants available.

Zabantu is a family of XLM-RoBERTa masked language models (roughly 80M to 250M params) trained from scratch on South African Bantu languages including Tshivenda, Zulu, Xhosa, Swati, Northern and Southern Sotho, Setswana and Xitsonga. It serves as a benchmark for low-resource Bantu language NLP. It was built by the Data Science for Social Impact group at the University of Pretoria.