@inproceedings{hsieh-2025-compact,
    title = "A Compact {W}hisper+{L}o{RA} Baseline for {T}aiwanese {H}akka {ASR} in {FSR}-2025",
    author = "Hsieh, Hung-Ting",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2025.rocling-main.55/",
    pages = "467--470",
    ISBN = "979-8-89176-379-1",
    abstract = "We present a compact baseline for the For- mosa Speech Recognition (FSR-2025) Tai- wanese Hakka ASR challenge. Our system fine-tunes Whisper-large-v2 (Track 1) and Whisper-large-v3-turbo (Track 2) (Radford et al., 2022) with LoRA (Hu et al., 2021), under a consistent normalization policy and balanced speaker-based dev splits. On the official warm-up set, we obtain 10.94{\%} CER for Track 1 (Hanzi) and 28.48{\%} SER for Track 2 (Pinyin). We provide simple, reproducible pipelines covering data prepa- ration, training, inference, and evaluation, without using external data or language models."
}