arztz/ocr-tesseract repository overview

FROM python:3.7-slim WORKDIR /app RUN apt-get update &&
apt-get install -y --no-install-recommends
libleptonica-dev
automake
libtool
pkg-config
libsdl-pango-dev
libicu-dev
libcairo2-dev
bc
unzip
python3-dev
build-essential
git \ wget \ libsm6
libxext6 \ libxrender-dev \ build-essential
poppler-utils &&
wget https://dvc.org/deb/dvc.list⁠ -O /etc/apt/sources.list.d/dvc.list &&
apt update &&
apt install dvc &&
rm -rf /var/lib/apt/lists/*

RUN wget https://github.com/tesseract-ocr/tesseract/archive/4.1.1.zip⁠ &&
unzip 4.1.1.zip &&
cd tesseract-4.1.1 &&
./autogen.sh &&
./configure &&
make &&
make install && \ ldconfig &&
tesseract --version RUN pip install torch==1.4.0+cpu \
torchvision==0.5.0+cpu \
-f https://download.pytorch.org/whl/torch_stable.html⁠