Add the English PP-OCRv4 set additively (det, rec, en_dict) — #2441 Decision 3 (PR #3024); sources: ModelScope RapidAI/RapidOCR v3.8.0, the exact paths docling 2.99.0 resolves
310479b verified | { | |
| "schema": "superlinked-model-artifact-sources-v1", | |
| "artifact": { | |
| "intended_repo_id": "superlinked/docling-artifacts", | |
| "runtime": "docling", | |
| "runtime_version": "2.99.0", | |
| "artifact_file_count": 12, | |
| "artifact_size_bytes": 410718353, | |
| "selection": { | |
| "layout": "docling-layout-heron", | |
| "table_structure": "tableformer-accurate", | |
| "ocr": "rapidocr-onnxruntime-pp-ocrv4-chinese+english", | |
| "font_included": false | |
| } | |
| }, | |
| "sources": [ | |
| { | |
| "name": "Docling Layout Heron", | |
| "upstream_repo": "https://huggingface.co/docling-project/docling-layout-heron", | |
| "upstream_revision": "8f39ad3c0b4c58e9c2d2c84a38465abf757272d8", | |
| "license": "Apache-2.0", | |
| "license_evidence": "https://huggingface.co/docling-project/docling-layout-heron/blob/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8/README.md", | |
| "files": [ | |
| { | |
| "path": "docling-project--docling-layout-heron/config.json", | |
| "size_bytes": 3268, | |
| "sha256": "fdea30805ce2f5666b147fca941dcdd27ad468e27d6ed21902207d3da056a97d", | |
| "source_url": "https://huggingface.co/docling-project/docling-layout-heron/resolve/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8/config.json" | |
| }, | |
| { | |
| "path": "docling-project--docling-layout-heron/model.safetensors", | |
| "size_bytes": 171658996, | |
| "sha256": "00333a43451945aaf89db8ca9c0a17e75d1537c17db60fdb91aa95f4c7929e0c", | |
| "source_url": "https://huggingface.co/docling-project/docling-layout-heron/resolve/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8/model.safetensors" | |
| }, | |
| { | |
| "path": "docling-project--docling-layout-heron/preprocessor_config.json", | |
| "size_bytes": 444, | |
| "sha256": "cd38cd59999e7a95d68e487fbe5132df3d4e5c32a0836add57e6126ba0c4eaf1", | |
| "source_url": "https://huggingface.co/docling-project/docling-layout-heron/resolve/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8/preprocessor_config.json" | |
| } | |
| ] | |
| }, | |
| { | |
| "name": "Docling TableFormer", | |
| "upstream_repo": "https://huggingface.co/docling-project/docling-models", | |
| "upstream_revision": "fc0f2d45e2218ea24bce5045f58a389aed16dc23", | |
| "upstream_release": "v2.3.0", | |
| "license": "CDLA-Permissive-2.0", | |
| "license_evidence": "https://huggingface.co/docling-project/docling-models/blob/fc0f2d45e2218ea24bce5045f58a389aed16dc23/README.md", | |
| "files": [ | |
| { | |
| "path": "docling-project--docling-models/model_artifacts/tableformer/accurate/tableformer_accurate.safetensors", | |
| "size_bytes": 212758388, | |
| "sha256": "2a7d6c924b3cd12fb99a09280ca9c33a89c5d60b93253617d2e088c1a40374d9", | |
| "source_url": "https://huggingface.co/docling-project/docling-models/resolve/fc0f2d45e2218ea24bce5045f58a389aed16dc23/model_artifacts/tableformer/accurate/tableformer_accurate.safetensors" | |
| }, | |
| { | |
| "path": "docling-project--docling-models/model_artifacts/tableformer/accurate/tm_config.json", | |
| "size_bytes": 7060, | |
| "sha256": "984e122ceb8ccf84d84c9d2882f6f2302a44b4f1e577babd6289892c36f3cffd", | |
| "source_url": "https://huggingface.co/docling-project/docling-models/resolve/fc0f2d45e2218ea24bce5045f58a389aed16dc23/model_artifacts/tableformer/accurate/tm_config.json" | |
| } | |
| ] | |
| }, | |
| { | |
| "name": "RapidOCR PP-OCRv4 Chinese ONNX", | |
| "upstream_repo": "https://www.modelscope.cn/models/RapidAI/RapidOCR", | |
| "upstream_release": "v3.8.0", | |
| "license": "Apache-2.0", | |
| "copyright_notice": "RapidOCR states that OCR model copyright is held by Baidu.", | |
| "license_evidence": "https://github.com/RapidAI/RapidOCR#license", | |
| "files": [ | |
| { | |
| "path": "RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx", | |
| "size_bytes": 585532, | |
| "sha256": "e47acedf663230f8863ff1ab0e64dd2d82b838fceb5957146dab185a89d6215c", | |
| "source_url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx" | |
| }, | |
| { | |
| "path": "RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx", | |
| "size_bytes": 4745517, | |
| "sha256": "d2a7720d45a54257208b1e13e36a8479894cb74155a5efe29462512d42f49da9", | |
| "source_url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx" | |
| }, | |
| { | |
| "path": "RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx", | |
| "size_bytes": 10857958, | |
| "sha256": "48fc40f24f6d2a207a2b1091d3437eb3cc3eb6b676dc3ef9c37384005483683b", | |
| "source_url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx" | |
| }, | |
| { | |
| "path": "RapidOcr/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile/ppocr_keys_v1.txt", | |
| "size_bytes": 26249, | |
| "sha256": "28b2362ad4ab2dc38769aa72feb535e3a9ddb3fd2a7585a05920e6393b1dc7f7", | |
| "source_url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile/ppocr_keys_v1.txt" | |
| } | |
| ] | |
| }, | |
| { | |
| "name": "RapidOCR PP-OCRv4 English ONNX", | |
| "upstream_repo": "https://www.modelscope.cn/models/RapidAI/RapidOCR", | |
| "upstream_release": "v3.8.0", | |
| "license": "Apache-2.0", | |
| "copyright_notice": "RapidOCR states that OCR model copyright is held by Baidu.", | |
| "license_evidence": "https://github.com/RapidAI/RapidOCR#license", | |
| "files": [ | |
| { | |
| "path": "RapidOcr/onnx/PP-OCRv4/det/en_PP-OCRv3_det_mobile.onnx", | |
| "size_bytes": 2421707, | |
| "sha256": "ea07c15d38ac40cd69da3c493444ec75b44ff23840553ff8ba102c1219ed39c2", | |
| "source_url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/onnx/PP-OCRv4/det/en_PP-OCRv3_det_mobile.onnx" | |
| }, | |
| { | |
| "path": "RapidOcr/onnx/PP-OCRv4/rec/en_PP-OCRv4_rec_mobile.onnx", | |
| "size_bytes": 7653044, | |
| "sha256": "e8770c967605983d1570cdf5352041dfb68fa0c21664f49f47b155abd3e0e318", | |
| "source_url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/onnx/PP-OCRv4/rec/en_PP-OCRv4_rec_mobile.onnx" | |
| }, | |
| { | |
| "path": "RapidOcr/paddle/PP-OCRv4/rec/en_PP-OCRv4_rec_mobile/en_dict.txt", | |
| "size_bytes": 190, | |
| "sha256": "5662df9d2d03f0e8ca0d3b0649d6acbab904b6a14b3d3521463c71c37c668ce3", | |
| "source_url": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/paddle/PP-OCRv4/rec/en_PP-OCRv4_rec_mobile/en_dict.txt" | |
| } | |
| ] | |
| } | |
| ] | |
| } | |