| ## Description | |
| Afroscope-model is a language identification (LID) model from the AfroScope project, fine-tuned on [Serengeti](https://huggingface.co/UBC-NLP/serengeti), supporting 713 African languages. | |
| For more details on the supported languages and performance, as well as significant changes from previous versions, please refer to LINK_HERE. | |
| - **Dataset:** [dataset](https://huggingface.co/datasets/14kwonss/afroscope-data) | |
| - **Repository:** [github](https://github.com/skwon01-UBC/AfroScope?tab=readme-ov-file) | |
| - **Paper:** [Arxiv](https://www.arxiv.org/pdf/2601.13346) | |
| --- | |
| ## How to use | |
| Here is how to use this model to detect the language of a given text: | |
| ```python | |
| from transformers import pipeline | |
| afroscope_model = pipeline("text-classification", model='UBC-NLP/afroscope-model') | |
| input_text="Ninyepuní íne εtɩε, bε ewǐe Jesi ɔnʋ lεfε kʋkʋkpɔ cε." | |
| result = afroscope_model(input_text) | |
| # Extract the label and score from the first result | |
| language = result[0]['label'] | |
| score = result[0]['score'] | |
| print(f"detected langauge: {language}\tscore: {round(score*100, 2)}") | |
| ``` | |
| ## Citation | |
| ```bibtex | |
| @article{kwon2026afroscope, | |
| title={AfroScope: A Framework for Studying the Linguistic Landscape of Africa}, | |
| author={Kwon, Sang Yun and Elmadany, AbdelRahim and Abdul-Mageed, Muhammad}, | |
| journal={arXiv preprint arXiv:2601.13346}, | |
| year={2026} | |
| } | |
| ``` |