diff --git a/paddleocr.py b/paddleocr.py index 4c7c4221bc..89bbd98a14 100644 --- a/paddleocr.py +++ b/paddleocr.py @@ -110,6 +110,10 @@ def _import_file(module_name, file_path, make_importable=False): "url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/ppocr_keys_v1.txt", }, + "ch_doc": { + "url": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-OCRv4_server_rec_doc_infer.tar", + "dict_path": "./ppocr/utils/ppchatocr_v2_dict_fix.txt", + }, "en": { "url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/english/en_PP-OCRv4_rec_infer.tar", "dict_path": "./ppocr/utils/en_dict.txt", @@ -512,7 +516,7 @@ def parse_lang(lang): ), "param lang must in {}, but got {}".format( MODEL_URLS["OCR"][DEFAULT_OCR_MODEL_VERSION]["rec"].keys(), lang ) - if lang == "ch": + if lang in ["ch", "ch_doc"]: det_lang = "ch" elif lang == "structure": det_lang = "structure"