@inproceedings{singh-warstadt-2026-fine,
    title = "Fine-tuning Whisper Across 81 Languages",
    author = "Singh, Shivam  and
      Warstadt, Alex",
    editor = "Voigt, Rob  and
      Warstadt, Alex  and
      Feldman, Naomi  and
      Linzen, Tal",
    booktitle = "Proceedings of the Society for Computation in Linguistics 2026",
    month = jul,
    year = "2026",
    address = "San Diego, CA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.37/",
    pages = "408--410",
    ISBN = "979-8-89176-412-5",
    abstract = "We fine-tune Whisper large-v3 independently on each of the 81 languages in the FLEURS benchmark. Fine-tuning improves WER for all 81 languages, reducing it by nearly 30{\%} on average. However, improvement varies widely, and the language{'}s writing system is the best predictor of success. Latin and Cyrillic script languages reach single-digit WERs, while languages with unique scripts (Thai, Georgian, Burmese, Khmer) benefit least. We further show that Whisper{'}s BPE compression ratio predicts fine-tuning headroom (Spearman {\ensuremath{\rho}} {\ensuremath{\approx}} {\ensuremath{-}}0.78), pointing to tokenization as the underlying bottleneck. We will release model weights upon publication."
}