@inproceedings{gamboni-2025-fine,
    title = "Fine-Tuning Whisper for {K}ildin {S}ami",
    author = "Gamboni, Enzo",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      Rie{\ss}ler, Michael  and
      Morooka, Eiaki V.  and
      Kharlashkin, Lev},
    booktitle = "Proceedings of the 10th International Workshop on Computational Linguistics for Uralic Languages",
    month = dec,
    year = "2025",
    address = "Joensuu, Finland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2026-01/2025.iwclul-1.13/",
    pages = "106--111",
    ISBN = "979-8-89176-360-9",
    abstract = "For this study, Whisper, an automatic speech recognition software, was fine-tuned on Kildin Sami, an endangered and low-resource Uralic language, using an automatic speech recognition-tailored dataset of less than 30 minutes. Three different Whisper models were trained with this dataset{---}each one with a different base language (English, Finnish, or Russian){---}to examine which model provided the best result. Results were measured using Word Error Rate; fine-tuning the Russian-base Whisper model resulted in the lowest Word Error Rate at 68.55{\%}. While still high, this result is impressive for only a small amount of language-specific training data, and the training process yielded insights relevant for potential for further work."
}