@article{thethiomidatasetalargescalemultimodalcor,
  title = {The Thiomi Dataset: A Large-Scale Multimodal Corpus for Low-Resource African Languages},
  author = {Hillary Mutisya and John Mugane and Gavin Nyamboga and Brian Chege and Maryruth Gathoni},
  year = {2026},
  eprint = {2603.29244},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.29244},
}