Tag
该论文提出一个多粒度评估框架，结合字符错误率、音节错误率和分词错误率，评估藏语语音识别在多方言与不同适配策略下的表现，发现低字符错误率并不总带来更优的高层级指标，且 LoRA 适配在测试范围内仍逊于全量微调。
This paper presents the first systematic study of word segmentation for the extinct Tangut language, combining traditional lexicons, unlabeled text, and a pretrained character encoder to achieve high performance despite extreme resource scarcity.