arXiv:2610.36911 · v1

Developing a Speech Language Model for Basque

首次提交 2026-10-27 17:40

版本更新 2026-10-27 17:40

雷达观测 2026-10-29 00:35

摘要

Although the recent development of LLMs has paved the way for multi-modal interaction, minority languages face difficulties keeping pace. This work presents the first open Speech Language Model for Basque, designed for low-latency, end-to-end spoken interaction. Based on the LLaMA-Omni architecture, the system integrates a Latxa model as its backbone, transferring its Basque capabilities to the spoken modality by fine-tuning several modules. To address data scarcity, the English VoiceAssistant-400K corpus was translated into Basque, and the audio was synthesized using a Basque TTS. Evaluation results confirm the system's viability, achieving 3.86/5 in content quality, a 9.94% WER for spoken intelligibility, and a 3.07 UTMOS for audio quality. This work demonstrates that advanced spoken interaction systems can be developed using modular architectures and synthetic data even in low-resource languages.

作者备注：IberSPEECH2026 - Jornadas en Tecnologias del Habla and Iberian SLTech Workshop Events