PaddleOCR

# 版本 https://pypi.org/project/paddlepaddle/#history
# registry.baidubce.com/paddlepaddle/paddle:3.0.0b1-jupyter
# registry.baidubce.com/paddlepaddle/paddle:3.0.0b1
docker run --rm -it \
  -v $PWD:/paddle \
  --name paddle registry.baidubce.com/paddlepaddle/paddle:3.0.0b1 /bin/bash

from paddleocr import PaddleOCR, draw_ocr

# Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
# 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
ocr = PaddleOCR(use_angle_cls=True, lang="ch")
img_path = 'PaddleOCR/doc/imgs/11.jpg'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

# 显示结果
from PIL import Image
result = result[0]
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

uv venv --python 3.11
uv pip install paddlepaddle paddleocr

https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/fonts/PingFang-SC-Regular.ttf
https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/fonts/simfang.ttf
https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_rec_infer.tar
https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-LCNet_x1_0_doc_ori_infer.tar
https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/UVDoc_infer.tar
https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-LCNet_x1_0_textline_ori_infer.tar

pip install paddlepaddle

enable_mkldnn: False