Curated corpora for Setswana. Used to train PuoBERTa.
A two-stage QLoRA fine-tuning framework for high-fidelity Twi-to-English translation using Meta's NLLB-200. Explores large-scale synthetic pre-training and human-aligned refinement paradigms under strict 6GB VRAM hardware constraints
IsiZulu News (articles and headlines) and Siswati News (headlines) Corpora - za-isizulu-siswati-news-2022
Igbo-English code-mixed hate speech detection. HND final-year research project with a novel labeled dataset, trained classifier, and Kivy GUI.
Machine learning project for sentiment analysis of Hausa text using TF-IDF and classification models.
Pre-trained word2vec embeddings for various Bantu languages spoken across Africa
Add a description, image, and links to the african-nlp topic page so that developers can more easily learn about it.
To associate your repository with the african-nlp topic, visit your repo's landing page and select "manage topics."