| { |
| "model_name": "latin_PP-OCRv5_mobile_rec", |
| "model_type": "recognition", |
| "framework": "PaddleOCR", |
| "version": "PP-OCRv5", |
| "language_group": "latin", |
| "supported_languages": [ |
| "English", |
| "French", |
| "German", |
| "Afrikaans", |
| "Italian", |
| "Spanish", |
| "Bosnian", |
| "Portuguese", |
| "Czech", |
| "Welsh", |
| "Danish", |
| "Estonian", |
| "Irish", |
| "Croatian", |
| "Uzbek", |
| "Hungarian", |
| "Serbian (Latin)", |
| "Indonesian", |
| "Occitan", |
| "Icelandic", |
| "Lithuanian", |
| "Maori", |
| "Malay", |
| "Dutch", |
| "Norwegian", |
| "Polish", |
| "Slovak", |
| "Slovenian", |
| "Albanian", |
| "Swedish", |
| "Swahili", |
| "Tagalog", |
| "Turkish", |
| "Latin" |
| ], |
| "description": "PP-OCRv5 Latin script text recognition model (32 languages)", |
| "accuracy": 84.7, |
| "dataset": "3,111 Latin script images", |
| "original_format": "PaddlePaddle", |
| "converted_format": "ONNX", |
| "opset_version": 11, |
| "dictionary_file": "ppocrv5_latin_dict.txt", |
| "input_shape": "dynamic (batch_size, 3, 32, dynamic_width)", |
| "output_shape": "dynamic (batch_size, sequence_length, num_classes)", |
| "source": "https://github.com/PaddlePaddle/PaddleOCR", |
| "documentation": "https://www.paddleocr.ai/main/en/version3.x/algorithm/PP-OCRv5/PP-OCRv5_multi_languages.html", |
| "usage": { |
| "library": "onnxruntime", |
| "preprocessing": "Grayscale or RGB image, resized to height=32, normalized", |
| "postprocessing": "CTC decoding with character dictionary", |
| "dictionary_format": "One character per line, UTF-8 encoding" |
| } |
| } |
