Qwen3.5-0.8B-AinuOCR

Model Description

This is Qwen3.5-0.8B-based model, finetuned for OCR of Ainu texts written in カタカナ.

How to Use

from transformers import pipeline
img="https://huggingface.co/KoichiYasuoka/Qwen3.5-0.8B-AinuOCR/resolve/main/uwerankarap/orig/2026-01-31.jpg"
nlp=pipeline("image-text-to-text","KoichiYasuoka/Qwen3.5-0.8B-AinuOCR",max_new_tokens=1024)
doc=nlp([{"role":"user","content":[{"type":"image","image":img},{"type":"text","text":"OCR Ainu sentences."}]}])
print(doc[0]["generated_text"][1]["content"])

Reference

安岡孝一, 安岡素子: Qwen3.5によるカタカナアイヌ語OCRの開発, 情報処理学会研究報告, Vol.2026-CH-141『人文科学とコンピュータ』, No.3 (2026年5月16日), pp.1-5.