首个开源巴斯克语语音语言模型发布
Developing a Speech Language Model for Basque
巴斯克语也能做语音对话了，用 Latxa 加合成数据就搞定，做小语种语音模型可以参考这套做法。
研究人员基于 LLaMA-Omni 架构，以 Latxa 模型为骨干，微调多个模块构建了首个开源巴斯克语语音语言模型。为解决数据稀缺问题，团队将英文 VoiceAssistant-400K 语料翻译成巴斯克语，并用巴斯克 TTS 合成音频。评测中该系统在内容质量上获得 3.86/5，语音可懂度 WER 为 9.94%，音频质量 UTMOS 得分为 3.07。结果表明低资源语言也能用模块化架构加合成数据开发语音交互系统。
Developing a Speech Language Model for Basque
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.
