PaddleOCR-VL-1.5-Ainu

Model Description

This is PaddleOCR-VL-1.5-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/PaddleOCR-VL-1.5-Ainu/resolve/main/uwerankarap/orig/2026-01-31.jpg"
nlp=pipeline("image-text-to-text","KoichiYasuoka/PaddleOCR-VL-1.5-Ainu",max_new_tokens=2048)
doc=nlp([{"role":"user","content":[{"type":"image","image":img},{"type":"text","text":"OCR"}]}])
print(doc[0]["generated_text"][1]["content"])