@inproceedings{quispe-callanaupa-etal-2026-optimization,
title = "Optimization of Voice Translation Systems for Indigenous Languages: Retraining the {NLLB}-200 Model for the {Q}uechua{--}{S}panish Pair",
author = "Quispe Calla{\~n}aupa, Mitzuko Davis and
Toledo Bernal, Max Erixon and
Torres Bautista, Ronil Nilo and
Pumaccahua Huallpa, Patrick Michael",
editor = "Salesky, Elizabeth and
Anastasopoulos, Antonios and
Negri, Matteo and
Federico, Marcello",
booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
month = jul,
year = "2026",
address = "San Diego, USA (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwslt-1.35/",
pages = "316--317",
ISBN = "979-8-89176-411-8",
abstract = "This article describes the fine-tuning and incremental retraining process of the massive NLLB-200 model applied to the Quechua (Chanka and Collao variants) and Spanish language pair. Using a curated dataset of 22,891 parallel pairs, a robust cleaning strategy and optimized training for consumer hardware (NVIDIA RTX 3060) were implemented. The results demonstrate a progressive improvement in the BLEU metric, reaching a competitive state for translation tasks in low-resource scenarios, in line with the challenges posed by the IWSLT 2026 shared task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="quispe-callanaupa-etal-2026-optimization">
<titleInfo>
<title>Optimization of Voice Translation Systems for Indigenous Languages: Retraining the NLLB-200 Model for the Quechua–Spanish Pair</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mitzuko</namePart>
<namePart type="given">Davis</namePart>
<namePart type="family">Quispe Callañaupa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="given">Erixon</namePart>
<namePart type="family">Toledo Bernal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronil</namePart>
<namePart type="given">Nilo</namePart>
<namePart type="family">Torres Bautista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="given">Michael</namePart>
<namePart type="family">Pumaccahua Huallpa</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 23rd International Conference on Spoken Language Translation (IWSLT 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-411-8</identifier>
</relatedItem>
<abstract>This article describes the fine-tuning and incremental retraining process of the massive NLLB-200 model applied to the Quechua (Chanka and Collao variants) and Spanish language pair. Using a curated dataset of 22,891 parallel pairs, a robust cleaning strategy and optimized training for consumer hardware (NVIDIA RTX 3060) were implemented. The results demonstrate a progressive improvement in the BLEU metric, reaching a competitive state for translation tasks in low-resource scenarios, in line with the challenges posed by the IWSLT 2026 shared task.</abstract>
<identifier type="citekey">quispe-callanaupa-etal-2026-optimization</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.35/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>316</start>
<end>317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimization of Voice Translation Systems for Indigenous Languages: Retraining the NLLB-200 Model for the Quechua–Spanish Pair
%A Quispe Callañaupa, Mitzuko Davis
%A Toledo Bernal, Max Erixon
%A Torres Bautista, Ronil Nilo
%A Pumaccahua Huallpa, Patrick Michael
%Y Salesky, Elizabeth
%Y Anastasopoulos, Antonios
%Y Negri, Matteo
%Y Federico, Marcello
%S Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA (in-person and online)
%@ 979-8-89176-411-8
%F quispe-callanaupa-etal-2026-optimization
%X This article describes the fine-tuning and incremental retraining process of the massive NLLB-200 model applied to the Quechua (Chanka and Collao variants) and Spanish language pair. Using a curated dataset of 22,891 parallel pairs, a robust cleaning strategy and optimized training for consumer hardware (NVIDIA RTX 3060) were implemented. The results demonstrate a progressive improvement in the BLEU metric, reaching a competitive state for translation tasks in low-resource scenarios, in line with the challenges posed by the IWSLT 2026 shared task.
%U https://aclanthology.org/2026.iwslt-1.35/
%P 316-317
Markdown (Informal)
[Optimization of Voice Translation Systems for Indigenous Languages: Retraining the NLLB-200 Model for the Quechua–Spanish Pair](https://aclanthology.org/2026.iwslt-1.35/) (Quispe Callañaupa et al., IWSLT 2026)
ACL