Aller au contenu
ModelPrésentéExterne
Browse files

Pp Ocrv6 One Piece Bubble Line Rec

Browser-ready OCR package for Projet Poneglyph. The pipeline detects text lines inside a manga bubble with YOLO26n, stitches the detected lines into one horizontal crop, decodes it with fine-tuned PP-OCRv6, then...

TypeOtherVersionRevision 10b932dBClasse

Source du modèle

Type
Other
Taille du fichier
9,60–73,2 MB
Version
vRevision 10b932d
Mis à jour
23 oct. 2026
Téléchargements
6
Source
Hugging Face

Description de la source

PP-OCRv6 One Piece Bubble Line Recognition

Browser-ready OCR package for Projet Poneglyph. The pipeline detects text lines inside a manga bubble with YOLO26n, stitches the detected lines into one horizontal crop, decodes it with fine-tuned PP-OCRv6, then applies a conservative train-derived spacing/case postprocess from onnx/browser_manifest.json.

Current browser result

  • Hugging Face repo: Remidesbois/pp-ocrv6-one-piece-bubble-line-rec
  • Validation CER: 0.017155317360235393 (1.7155%)
  • Validation exact match: 0.7514693534844669 (75.15%)
  • Test CER: 0.014505395907584179 (1.4505%)
  • Test exact match: 0.7596390484003281 (75.96%)
  • Exported bubble images: 7821
  • Bubbles without detected lines: 22
  • Duplicate line-box bubbles: 0

These metrics are computed from the official 2026-06-29 release prediction CSVs after applying the browser postprocess rules trained only from the train split. The raw 2026-06-29 release baseline was validation 1.9204% CER / 71.62% exact and test 1.7097% CER / 71.21% exact.

Model and detector evidence

  • YOLO mAP50: 0.98917488275913
  • YOLO mAP50-95: 0.8715335950608416
  • Line detector mAP50: 0.995
  • Line detector mAP50-95: 0.8926965538059898
  • ONNX parity text match: true

Files

  • onnx/bubble_line_detector_yolo26n.onnx
  • onnx/ppocrv6_bubble_line_rec.onnx
  • onnx/ppocrv6_bubble_line_rec_webgpu.onnx
  • onnx/browser_manifest.json
  • onnx/pipeline_manifest.json
  • onnx/ppocrv6_postprocess_rules.json
  • postprocess_official_metrics.json
  • training_metrics.json
  • yolo_metrics.json
  • validation_predictions.csv
  • test_predictions.csv

The frontend model key is ppocrv6Line.

Sources

1 source
Hugging FacePrincipalVersion 10b932d4aadca2830850ccf5951116597404bef8
huggingface.co/Remidesbois/pp-ocrv6-one-piece-bubble-line-rec/tree/10b932d4aadca2830850ccf5951116597404bef8

Vérifié 23 oct.

Download files

Artefacts du modèle

4 artefacts

model.safetensors

safetensors · 73,2 MB · SHA-256 ca4a6505132c…9d7e · Hugging Face

Download file

onnx/bubble_line_detector_yolo26n.onnx

onnx · 9,60 MB · SHA-256 b8a7d12cbb65…3505 · Hugging Face

Download file

onnx/ppocrv6_bubble_line_rec_webgpu.onnx

onnx · 73,0 MB · SHA-256 73e599ee88fe…31e3 · Hugging Face

Download file

onnx/ppocrv6_bubble_line_rec.onnx

onnx · 73,0 MB · SHA-256 d85e44d24c05…0d1a · Hugging Face

Download file

Extraits de sources

3 extraits

--- pipeline_tag: image-to-text license: apache-2.0 tags: - ocr - manga - ppocrv6 - yolo - onnx --- # PP-OCRv6 One Piece Bubble Line Recognition Browser-ready OCR package for Projet Poneglyph. The pipeline detects text lines inside a manga bubble with YOLO26n, stitches the detected lines into one horizontal crop, decodes it with fine-tuned PP-OCRv6, then applies a conservative train-derived spacing/case postprocess from `onnx/browser_manifest.json`. ## Current browser result - Hugging Face repo: `Remidesbois/pp-ocrv6-one-piece-bubble-line-rec` - Validation CER: `0.017155317360235393` (`1.7155%`) - Validation exact match: `0.7514693534844669` (`75.15%`) - Test CER: `0.014505395907584179` (`1.4505%`) - Test exact match: `0.7596390484003281` (`75.96%`) - Exported bubble images: `7821` - Bubbles without detected lines: `22` - Duplicate line-box bubbles: `0` These metrics are computed from the official 2026-06-29 release prediction CSVs after applying the browser postprocess rules trained only from the train split. The raw 2026-06-29 release baseline was validation `1.9204% CER / 71.62% exact` and test `1.7097% CER / 71.21% exact`. ## Model and detector evidence - YOLO mAP50: `0.98917488275913` - YOLO mAP50-95: `0.8715335950608416` - Line detector mAP50: `0.995` - Line detector mAP50-95: `0.8926965538059898` - ONNX parity text match: `true` ## Files - `onnx/bubble_line_detector_yolo26n.onnx` - `onnx/ppocrv6_bubble_line_rec.onnx` - `onnx/ppocrv6_bubble_line_rec_webgpu.onnx` - `onnx/browser_manifest.json` - `onnx/pipeline_manifest.json` - `onnx/ppocrv6_postprocess_rules.json` - `postprocess_official_metrics.json` - `training_metrics.json` - `yolo_metrics.json` - `validation_predictions.csv` - `test_predictions.csv` The frontend model key is `ppocrv6Line`.

Source context: 6 downloads · 0 likes · Pipeline image-to-text · Repo Remidesbois/pp-ocrv6-one-piece-bubble-line-rec

Source context: 34 downloads · 0 likes · Pipeline image-to-text · Repo Remidesbois/pp-ocrv6-one-piece-bubble-line-rec