astrocket / EasyOCR

EasyOCR model serving API

EasyOCR Server

• EasyOCR model serving API.
• Korean, English model included.

Get your gpu cloud -> https://www.paperspace.com/

install nvidia driver

install driver scanner

sudo apt install -y ubuntu-drivers-common

Find your

ubuntu-drivers devices

install your driver

sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt update
apt-cache search nvidia | grep <recommended-driver-name>
sudo apt-get install <recommended-driver-name>

sudo reboot

install cuda toolkit

sudo apt update
sudo apt install nvidia-cuda-toolkit

nvcc --version

install docker, docker-compose

install docker

sudo apt update
sudo apt install apt-transport-https ca-certificates curl software-properties-common
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu focal stable"
apt-cache policy docker-ce
sudo apt install docker-ce
sudo systemctl status docker
sudo usermod -aG docker ${USER}

install docker-compose

sudo curl -L "https://github.com/docker/compose/releases/download/1.29.2/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
sudo chmod +x /usr/local/bin/docker-compose
docker-compose --version

set .env

touch .env

.env

API_TOKEN=password

start serving

local

docker-compose -f docker-compose.local.yml up --build

production

docker-compose up -d

references

cuda driver installation

docker installation

easy ocr training (korean)