Mapudungun-Spanish Speech Translation: A Low-Resource End-to-End System for the IWSLT 2026 Shared Task

Diego Alberto Barriga Martínez, Amilkar Gazque, Mikel Segura Elizalde, Carlos Daniel Hernandez Mena, Ximena Gutierrez-Vasques, Ivan Vladimir Meza Ruiz


Abstract
We present an end-to-end speech translation system for Mapudungun–Spanish developed for the IWSLT 2026 low-resource task. Building on the Canary-1B-v2 model, we apply parameter-efficient fine-tuning with a lightweight adapter and leverage an English-centered configuration as a proxy to enable translation. Experiments show that the system captures key phonetic patterns despite limited data, though it exhibits biases toward repetitive Spanish outputs. Our results highlight both the feasibility and the challenges of adapting multilingual foundation models to low-resource Indigenous languages.
Anthology ID:
2026.iwslt-1.26
Volume:
Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
Month:
July
Year:
2026
Address:
San Diego, USA (in-person and online)
Editors:
Elizabeth Salesky, Antonios Anastasopoulos, Matteo Negri, Marcello Federico
Venues:
IWSLT | WS
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
232–237
Language:
URL:
https://aclanthology.org/2026.iwslt-1.26/
DOI:
Bibkey:
Cite (ACL):
Diego Alberto Barriga Martínez, Amilkar Gazque, Mikel Segura Elizalde, Carlos Daniel Hernandez Mena, Ximena Gutierrez-Vasques, and Ivan Vladimir Meza Ruiz. 2026. Mapudungun-Spanish Speech Translation: A Low-Resource End-to-End System for the IWSLT 2026 Shared Task. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 232–237, San Diego, USA (in-person and online). Association for Computational Linguistics.
Cite (Informal):
Mapudungun-Spanish Speech Translation: A Low-Resource End-to-End System for the IWSLT 2026 Shared Task (Barriga Martínez et al., IWSLT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwslt-1.26.pdf