**摘要**
This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman, an endangered Australian indigenous language into English. The significant challenge we face is the lack of large-scale training data: in fact, we only have 6 hours of annotated audio. Therefore, while it is common practice to train a single model for transcription and translation using l
👤 作者: Ziheng Zhang, Yunzhong Hou, Naijing Liu, Liang Zheng

---
🔗 **[WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data](https://arxiv.org/abs/2605.13846v1)**

> WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-05-15 08:00