Skip to content
ModelListedExternal
Browse files

Yolov11x Codh Char

This is a YOLOv11x model fine-tuned for detecting and recognizing characters in Japanese historical documents (古典籍/Koten-seki). The model is trained on the 日本古典籍くずし字データセット (CODH Kuzushiji Dataset).

KindOtherVersionRevision 00373a8

Model source

Kind
Other
File size
38.3–218 MB
Version
vRevision 00373a8
Updated
Sep 22, 2026
Downloads
3
Source
Hugging Face

Source description

YOLOv11x CODH Character

Model Description

This is a YOLOv11x model fine-tuned for detecting and recognizing characters in Japanese historical documents (古典籍/Koten-seki). The model is trained on the 日本古典籍くずし字データセット (CODH Kuzushiji Dataset).

Intended Uses

  • Character detection in historical Japanese manuscripts
  • Kuzushiji (くずし字) character localization
  • Pre-processing for OCR pipelines on classical Japanese texts

How to Use

from ultralytics import YOLO

# Load model
model = YOLO("nakamura196/yolov11x-codh-char")

# Run inference
results = model.predict("your_image.jpg", conf=0.25, iou=0.45)

# Process results
for result in results:
    boxes = result.boxes
    print(boxes)

Or download the model file directly:

from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="nakamura196/yolov11x-codh-char", filename="best.pt")

Training Data

The model was trained on the CODH Kuzushiji Character Shape Dataset, which contains character images from various Japanese historical documents.

Model Architecture

  • Base Model: YOLOv11x (extra-large variant)
  • Task: Object Detection
  • Framework: Ultralytics

Limitations

  • Optimized for historical Japanese documents; may not perform well on modern printed text
  • Performance may vary depending on the document quality and writing style

Citation

If you use this model, please cite the original dataset:

@misc{codh_kuzushiji,
  title={CODH Kuzushiji Character Shape Dataset},
  author={Center for Open Data in the Humanities (CODH)},
  url={http://codh.rois.ac.jp/char-shape/}
}

License

MIT License

Sources

1 source
Hugging FacePrimaryVersion 00373a8137083b4cbbc54c4e5fcf509dc28db79c
huggingface.co/nakamura196/yolov11x-codh-char/tree/00373a8137083b4cbbc54c4e5fcf509dc28db79c

Verified Sep 9

Download files

Model artifacts

3 artifacts

best.onnx

onnx · 218 MB · SHA-256 28eab29a1bf7…957e · Hugging Face

Download file

best.pt

pt · 109 MB · SHA-256 cdff382908ed…c988 · Hugging Face

Download file

rtmdet-line.onnx

onnx · 38.3 MB · SHA-256 f46267754d40…090c · Hugging Face

Download file

Source excerpts

2 excerpts

--- license: mit library_name: ultralytics tags: - object-detection - yolo - yolov11 - japanese - kuzushiji - character-recognition - historical-documents datasets: - codh/kuzushiji language: - ja pipeline_tag: object-detection --- # YOLOv11x CODH Character ## Model Description This is a YOLOv11x model fine-tuned for detecting and recognizing characters in Japanese historical documents (古典籍/Koten-seki). The model is trained on the [日本古典籍くずし字データセット (CODH Kuzushiji Dataset)](http://codh.rois.ac.jp/char-shape/). ## Intended Uses - Character detection in historical Japanese manuscripts - Kuzushiji (くずし字) character localization - Pre-processing for OCR pipelines on classical Japanese texts ## How to Use ```python from ultralytics import YOLO # Load model model = YOLO("nakamura196/yolov11x-codh-char") # Run inference results = model.predict("your_image.jpg", conf=0.25, iou=0.45) # Process results for result in results: boxes = result.boxes print(boxes) ``` Or download the model file directly: ```python from huggingface_hub import hf_hub_download model_path = hf_hub_download(repo_id="nakamura196/yolov11x-codh-char", filename="best.pt") ``` ## Training Data The model was trained on the [CODH Kuzushiji Character Shape Dataset](http://codh.rois.ac.jp/char-shape/), which contains character images from various Japanese historical documents. ## Model Architecture - **Base Model**: YOLOv11x (extra-large variant) - **Task**: Object Detection - **Framework**: Ultralytics ## Limitations - Optimized for historical Japanese documents; may not perform well on modern printed text - Performance may vary depending on the document quality and writing style ## Citation If you use this model, please cite the original dataset: ``` @misc{codh_kuzushiji, title={CODH Kuzushiji Character Shape Dataset}, author={Center for Open Data in the Humanities (CODH)}, url={http://codh.rois.ac.jp/char-shape/} } ``` ## License MIT License

Source context: 3 downloads · 1 likes · Pipeline object-detection · Library ultralytics · Repo nakamura196/yolov11x-codh-char