PaddleOCR

smilecatZh/PaddleOCR

PaddleOCR is a machine learning model from smilecatZh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

本仓库包含 PaddleOCR 的预训练模型文件,用于 PDF 表格识别和 OCR 任务。

Downloads · 30 days

Access

Public

Updated Mar 20, 2026

Repo size

320 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pdiparams409 MB · 94%

At a glance

License: apache-2.0
Access: Public
Created: Mar 19, 2026
Updated: Mar 20, 2026
SHA: fe83da4f

Model card

From the Hugging Face model README

PaddleOCR 模型文件

本仓库包含 PaddleOCR 的预训练模型文件,用于 PDF 表格识别和 OCR 任务。

模型列表

中文模型 (CH)

检测模型: ch_PP-OCRv4_det_server_infer
识别模型: ch_PP-OCRv4_rec
表格模型: table_model

英文模型 (EN)

检测模型: en_PP-OCRv3_det_infer
识别模型: en_PP-OCRv3_rec_infer

其他模型

版面分析: picodet_lcnet_x1_0_fgd_layout_table_infer
SER模型: ser_LayoutXLM_xfun_zh_infer
方向分类: ch_ppocr_mobile_v2.0_cls_slim_infer

使用方法

from paddleocr import PPStructure

# 下载模型后指定路径
table_engine = PPStructure(
    show_log=True,
    rec_model_dir='./model/CH/rec_model/ch_PP-OCRv4_rec',
    det_model_dir='./model/CH/det_model/ch_PP-OCRv4_det_server_infer',
    layout_model_dir='./model/layout_model/picodet_lcnet_x1_0_fgd_layout_table_infer',
    layout_dict_path='./model/layout_model/layout_table_dict.txt',
    lang='ch',
    recovery=True,
    type='structure',
)

许可证

Apache 2.0

License: apache-2.0
Languages: zh, en
Created: Mar 19, 2026
Updated: Mar 20, 2026