ppu-paddle-ocr-models (PP-OCRv5 mobile, multilingual)

PP-OCRv5 mobile (multilingual) ONNX model weights + character dictionary, mirrored as a fallback CDN for pdfmarkdown.app's in-browser OCR. The primary CDN is jsDelivr (npm package pdfmarkdown-ppocrv5-models); HuggingFace's resolve/main serves as the second tier when jsDelivr is unavailable.

Files

Path	Purpose
detection/PP-OCRv5_mobile_det_infer.ort	Text detection model (ORT format)
recognition/PP-OCRv5_mobile_rec_infer.onnx	Text recognition model (ONNX, multilingual)
recognition/ppocrv5_dict.txt	Recognition character dictionary

Resolve URLs

https://huggingface.co/<user>/ppu-paddle-ocr-models/resolve/main/detection/PP-OCRv5_mobile_det_infer.ort
https://huggingface.co/<user>/ppu-paddle-ocr-models/resolve/main/recognition/PP-OCRv5_mobile_rec_infer.onnx
https://huggingface.co/<user>/ppu-paddle-ocr-models/resolve/main/recognition/ppocrv5_dict.txt

Attribution & License

Models are PP-OCRv5 from PaddleOCR, Apache-2.0. ONNX/ORT exports and dictionary sourced from PT-Perkasa-Pilar-Utama/ppu-paddle-ocr-models (Apache-2.0), redistributed unmodified for pdfmarkdown.app's browser OCR.