---
base_model: Qwen/Qwen3-VL-8B-Instruct
library_name: peft
pipeline_tag: image-text-to-text
license: apache-2.0
datasets:
- your-hf-username-or-org/rukopys-curated-mvp
language:
- uk
tags:
- peft
- lora
- qwen3-vl
- document-analysis
- handwriting-recognition
- htr
- ukrainian
- image-to-text
---

# RUKOPYS YOLO 11M Handwriting Region Detector

`AlexandreSheva/rukopys-yolo11m-detector` contains an Ultralytics YOLO 11M detector trained to localize handwritten regions in RUKOPYS manuscript page images. It is the layout-detection component of the RUKOPYS HTR pipeline and is intended to produce bounding boxes that can be passed to a recognizer or combined with page-level vision-language predictions.

## What It Does

- Detects handwritten text regions on scanned Ukrainian manuscript pages.
- Outputs YOLO object-detection boxes for one class: `handwritten`.
- Fits the RUKOPYS pipeline as the detector used before crop-level or page-level transcription.
- Supports reproducible experiments with the curated RUKOPYS MVP YOLO dataset.

## Quick Use

```python
from huggingface_hub import hf_hub_download
from ultralytics import YOLO

model_path = hf_hub_download(
    repo_id="AlexandreSheva/rukopys-yolo11m-detector",
    filename="weights/best.pt",
)
model = YOLO(model_path)
results = model.predict("page.jpg", imgsz=1536)
```

## Limitations
This model detects regions only; it does not transcribe text. It was trained for RUKOPYS-style Ukrainian manuscript pages, so validate it on other archives, scan qualities, and layouts before reuse. The detector is based on Ultralytics YOLO11 under AGPL-3.0, and the training data inherits CC BY-NC-SA 4.0 terms from the source dataset.

## Project Context

This model is part of a practical HTR system: raw RUKOPYS data curation, dataset packaging,
LoRA fine-tuning, inference, evaluation, and Kaggle-ready submission export. The goal is not only a
checkpoint, but a reproducible document-AI workflow for Ukrainian handwritten archives.