<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jaff-mohammadamini-2026-fleurs">
    <titleInfo>
        <title>FLEURS-Kobani: Extending FLEURS dataset for Northern Kurdish</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daban</namePart>
        <namePart type="given">Q</namePart>
        <namePart type="family">Jaff</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="family">Mohammadamini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Antonis</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stella</namePart>
            <namePart type="family">Markantonatou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Angela</namePart>
            <namePart type="family">Ralli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcos</namePart>
            <namePart type="family">Zampieri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stavros</namePart>
            <namePart type="family">Bompolas</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivian</namePart>
            <namePart type="family">Stamou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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→FLEURS-Kobani) yields the best ASR performance (WER 28.11, CER 9.84 on test). For end-to-end S2TT (KMR→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.</abstract>
    <identifier type="citekey">jaff-mohammadamini-2026-fleurs</identifier>
    <identifier type="doi">10.63317/267vdxnysvbe</identifier>
    <location>
        <url>https://aclanthology.org/2026.dialres-1.10/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>104</start>
            <end>109</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T FLEURS-Kobani: Extending FLEURS dataset for Northern Kurdish
%A Jaff, Daban Q.
%A Mohammadamini, Mohammad
%Y Anastasopoulos, Antonis
%Y Markantonatou, Stella
%Y Ralli, Angela
%Y Zampieri, Marcos
%Y Bompolas, Stavros
%Y Stamou, Vivian
%S Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca
%F jaff-mohammadamini-2026-fleurs
%X 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→FLEURS-Kobani) yields the best ASR performance (WER 28.11, CER 9.84 on test). For end-to-end S2TT (KMR→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.
%R 10.63317/267vdxnysvbe
%U https://aclanthology.org/2026.dialres-1.10/
%U https://doi.org/10.63317/267vdxnysvbe
%P 104-109

Markdown (Informal)

[FLEURS-Kobani: Extending FLEURS dataset for Northern Kurdish](https://aclanthology.org/2026.dialres-1.10/) (Jaff & Mohammadamini, DialRes 2026)

• FLEURS-Kobani: Extending FLEURS dataset for Northern Kurdish (Jaff & Mohammadamini, DialRes 2026)

ACL

• Daban Q. Jaff and Mohammad Mohammadamini. 2026. FLEURS-Kobani: Extending FLEURS dataset for Northern Kurdish. In Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective, pages 104–109, Palma de Mallorca. Association for Computational Linguistics.