@inproceedings{jaff-mohammadamini-2026-fleurs,
    title = "{FLEURS}-Kobani: Extending {FLEURS} dataset for {N}orthern {K}urdish",
    author = "Jaff, Daban Q.  and
      Mohammadamini, Mohammad",
    editor = "Anastasopoulos, Antonis  and
      Markantonatou, Stella  and
      Ralli, Angela  and
      Zampieri, Marcos  and
      Bompolas, Stavros  and
      Stamou, Vivian",
    booktitle = "Proceedings of the First Workshop on Dialects in {NLP} {---} A Resource Perspective",
    month = may,
    year = "2026",
    address = "Palma de Mallorca",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/revision-workflow/2026.dialres-1.10/",
    doi = "10.63317/267vdxnysvbe",
    pages = "104--109",
    abstract = "We present FLEURS-Kobani, a Northern Kurdish (ISO 639-3 KMR) spoken extension of FLEURS benchmark. Although FLEURS offers n-way parallel speech for 100+ languages, Northern Kurdish is absent, limits benchmarking automatic speech recognition and speech translation tasks for this language. The FLEURS-Kobani dataset consists of 5,162 validated utterances, totaling 18 hours and 24 minutes. As baselines, we fine-tuned Whisper v3-large for ASR and E2E S2TT. A two-stage fine-tuning strategy (Common Voice{\textrightarrow}FLEURS-Kobani) yields the best ASR performance (WER 28.11, CER 9.84 on test). For end-to-end S2TT (KMR{\textrightarrow}EN), Whisper achieves 8.68 BLEU on test; we additionally report pivot-derived targets and a cascaded S2TT setup. FLEURS-Kobani provides the first Northern Kurdish public benchmark for evaluation of ASR, S2TT and S2ST tasks. The data can be accessed (LINK IS BLANK DUE TO REVISION RULES) under CC BY 4.0 license."
}