Skip to content
PaddleOCR Text Recognition AI Platform & Data · PaddleOCR 3.7.0 Launch on AWS

Getting started

Launch PaddleOCR, sign in, and read one image.

You need: an AWS account that can subscribe, launch EC2, and start Session Manager. Install the AWS CLI and the Session Manager plugin on your workstation.

Watch on YouTube.

1. Subscribe

Open the PaddleOCR listing, choose View purchase options, review the terms, and subscribe. When the subscription is active, choose Launch your software.

2. Launch the instance

  1. Choose t3.large.
  2. Use an encrypted gp3 root volume of at least 32 GiB.
  3. Require IMDSv2.
  4. Attach an instance profile that can use Session Manager. No key pair and no inbound application rule are required.
  5. Choose Launch instance.

3. Connect and run the walkthrough

Session Manager starts as ssm-user. Wait for cloud-init, then:

sudo -iu ubuntu bash /opt/sushi/docs/demo.sh

4. Sign in

Forward port 8443 and open the local port over HTTPS. Sign in with the username and password from ~/.config/sushi/paddleocr/access.json.

aws ssm start-session --target <instance-id> \
  --document-name AWS-StartPortForwardingSession \
  --parameters '{"portNumber":["8443"],"localPortNumber":["8443"]}'

Upload a PNG or JPEG. The page shows the text and the boxes.

5. Read an image in the shell

On the instance, as ubuntu:

sushi-paddleocr-api ocr page.png

Replace page.png with your file. The command prints the text. Back up stored jobs before you replace the instance. See Operations.

Last updated November 1, 2026 · Suggest an improvement