在 MacOS M1 芯片上可以跑

1. Dockerfile

文件 docker/Dockerfile

FROM ubuntu:24.04

ARG DEBIAN_FRONTEND=noninteractive

RUN apt-get clean
RUN rm -rf /var/lib/apt/lists/*
RUN apt-get update --allow-releaseinfo-change

RUN apt install -y python3 python3-pip python3.12-venv

RUN python3 -m venv /opt/venv

ENV VIRTUAL_ENV=/opt/venv
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

RUN apt install -y libgl1 libglib2.0-0 libsm6 libxext6 libxrender1

RUN pip install --upgrade pip setuptools wheel

RUN pip install modelscope -i https://mirrors.aliyun.com/pypi/simple/  --trusted-host mirrors.aliyun.com

RUN pip install onnxruntime -i https://mirrors.aliyun.com/pypi/simple/  --trusted-host mirrors.aliyun.com

RUN pip install rapidocr -i https://pypi.tuna.tsinghua.edu.cn/simple/

2. docker-compose.yml

services:
  RapidOCR:
    build:
      context: docker
      dockerfile: ./Dockerfile
    image: rapidocr:v1

3. build docker 镜像

docker-compose -f docker-compose.yml build

检查 RapidOCR 是否安装成功

docker run --rm -it rapidocr:v1 rapidocr check

4. 在 python 中使用 RapidOCR

来源：https://rapidai.github.io/RapidOCRDocs/main/quickstart/

4.1 官方例子

from rapidocr import RapidOCR

engine = RapidOCR()

img_url = "https://github.com/RapidAI/RapidOCR/blob/main/python/tests/test_files/ch_en_num.jpg?raw=true"
result = engine(img_url)
print(result)
result.vis("vis_result.jpg")

4.2 批量处理本地图片

from rapidocr import RapidOCR
import sys

engine = RapidOCR()

for filename in sys.argv[1:]:
    filename = filename.strip()
    if not filename:
        continue
    img_url = filename
    print(f"file: {filename}", file=sys.stderr)
    result = engine(img_url)
    print(''.join(result.txts))

result 的数据结构如下

RapidOCROutput(
    boxes=array([[[  6.,   2.],
        [322.,   9.],
        [320., 104.],
        [  4.,  97.]],

        ...

       [[202., 391.],
        [287., 391.],
        [287., 413.],
        [202., 413.]]], dtype=float32),
    txts=('正品促销', '大桶装更划算', '强力去污符合国标', '40°C深度防冻不结冰', '日常价￥', '真击', '10.0起', '10.0起', '日常价￥', '底价', '5.8', '券后价￥', '起', '惊喜福利不容错过', '极速发货', '冰点标准', '破损就赔', '假一赔十'),
    scores=(0.99893, 0.9843, 0.97842, 0.93412, 0.81418, 0.66226, 0.99243, 0.99849, 0.81369, 0.99633, 0.9999, 0.83907, 0.99993, 0.99782, 0.99813, 0.99786, 0.92679, 0.99717),
    word_results=(None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None), elapse_list=[0.16008154186420143, 0.017705917358398438, 0.35501312371343374], elapse=0.5328005829360336)