@inproceedings{aurelian-tjiaranata-etal-2025-buinus,
    title = "{BUINUS} at {IWSLT}: Evaluating the Impact of Data Augmentation and {QL}o{RA}-based Fine-Tuning for {M}altese to {E}nglish Speech Translation",
    author = "Aurelian Tjiaranata, Filbert  and
      Alexandra Putra, Vallerie  and
      Presma Yulianrifat, Eryawan  and
      Akmal Hanif, Ikhlasul",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Anastasopoulos, Antonis",
    booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.iwslt-1.26/",
    pages = "269--273",
    ISBN = "979-8-89176-272-5",
    abstract = "This paper investigates approaches for the IWSLT low-resource track, Track 1 (speech-to-text translation) for the Maltese language, focusing on data augmentation and large pre-trained models. Our system combines Whisper for transcription and NLLB for translation, with experiments concentrated mainly on the translation stage. We observe that data augmentation leads to only marginal improvements, primarily for the smaller 600M model, with gains up to 0.0026 COMET points. These gains do not extend to larger models like the 3.3B NLLB, and the overall impact appears somewhat inconsistent. In contrast, fine-tuning larger models using QLoRA outperforms full fine-tuning of smaller models. Moreover, multi-stage fine-tuning consistently improves task-specific performance across all model sizes."
}