Fine-tuning Whisper Across 81 Languages

Shivam Singh; Alex Warstadt

Fine-tuning Whisper Across 81 Languages

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

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 ρ ≈ −0.78), pointing to tokenization as the underlying bottleneck. We will release model weights upon publication.

Anthology ID:: 2026.scil-main.37
Volume:: Proceedings of the Society for Computation in Linguistics 2026
Month:: July
Year:: 2026
Address:: San Diego, CA
Editors:: Rob Voigt, Alex Warstadt, Naomi Feldman, Tal Linzen
Venues:: SCiL | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 408–410
Language:
URL:: https://aclanthology.org/2026.scil-main.37/
DOI:
Bibkey:
Cite (ACL):: Shivam Singh and Alex Warstadt. 2026. Fine-tuning Whisper Across 81 Languages. In Proceedings of the Society for Computation in Linguistics 2026, pages 408–410, San Diego, CA. Association for Computational Linguistics.
Cite (Informal):: Fine-tuning Whisper Across 81 Languages (Singh & Warstadt, SCiL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.scil-main.37.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@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://aclanthology.org/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."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-warstadt-2026-fine">
    <titleInfo>
        <title>Fine-tuning Whisper Across 81 Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shivam</namePart>
        <namePart type="family">Singh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alex</namePart>
        <namePart type="family">Warstadt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Society for Computation in Linguistics 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Rob</namePart>
            <namePart type="family">Voigt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alex</namePart>
            <namePart type="family">Warstadt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naomi</namePart>
            <namePart type="family">Feldman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tal</namePart>
            <namePart type="family">Linzen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, CA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-412-5</identifier>
    </relatedItem>
    <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 \ensuremathρ \ensuremath\approx \ensuremath-0.78), pointing to tokenization as the underlying bottleneck. We will release model weights upon publication.</abstract>
    <identifier type="citekey">singh-warstadt-2026-fine</identifier>
    <location>
        <url>https://aclanthology.org/2026.scil-main.37/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>408</start>
            <end>410</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Fine-tuning Whisper Across 81 Languages
%A Singh, Shivam
%A Warstadt, Alex
%Y Voigt, Rob
%Y Warstadt, Alex
%Y Feldman, Naomi
%Y Linzen, Tal
%S Proceedings of the Society for Computation in Linguistics 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, CA
%@ 979-8-89176-412-5
%F singh-warstadt-2026-fine
%X 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 \ensuremathρ \ensuremath\approx \ensuremath-0.78), pointing to tokenization as the underlying bottleneck. We will release model weights upon publication.
%U https://aclanthology.org/2026.scil-main.37/
%P 408-410

Download as File

Markdown (Informal)

[Fine-tuning Whisper Across 81 Languages](https://aclanthology.org/2026.scil-main.37/) (Singh & Warstadt, SCiL 2026)

Fine-tuning Whisper Across 81 Languages (Singh & Warstadt, SCiL 2026)

ACL

Shivam Singh and Alex Warstadt. 2026. Fine-tuning Whisper Across 81 Languages. In Proceedings of the Society for Computation in Linguistics 2026, pages 408–410, San Diego, CA. Association for Computational Linguistics.