typhoon-ocr-open-vision-language-model-for-thai

【文档与办公】Document extraction is a core component of digital workflows, yet existing vision-language models (VLMs) predominantly favor high-resource languages. Thai presents additional challenges due to script complexity from non-latin letters, the absence of explicit word boundaries, and the prevalence of highly unstructured real-world documents, limiting the…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准