NVIDIA
Explore Models Blueprints GPUs
Terms of Use

|

Privacy Policy

|

Manage My Privacy

|

Contact

Copyright © 2025 NVIDIA Corporation

baidu

paddleocr

RUN ANYWHERE

Model for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.

optical character detectionoptical character recognitiontable extractiondata ingestionextractionnemo retrieverrun on rtx
Get API Key
API Reference
Accelerated by DGX Cloud
Deploying your application in production? Get started with a 90-day evaluation of NVIDIA AI Enterprise

Follow the steps below to download and run the NVIDIA NIM inference microservice for this model on your infrastructure of choice.

Prerequisites

  • NVIDIA GeForce RTX 4080 or above (see supported GPUs)
  • Install the latest NVIDIA GPU Driver on Windows (Version 570+)
  • Ensure virtualization is enabled in the system BIOS. In Windows, open Task Manager, select the Performance tab, and find Virtualization. If Disabled, see here to enable.

Step 1
Open the Windows Subsystem for Linux 2 - WSL2 - Distro

Install WSL2. For additional instructions refer to the documentation.

Once installed, open the NVIDIA-Workbench WSL2 distro using the following command in the Windows terminal.

wsl -d NVIDIA-Workbench

Step 2
Run the Container

$ podman login nvcr.io
Username: $oauthtoken
Password: <PASTE_API_KEY_HERE>

Pull and run the NVIDIA NIM with the command below.

export NGC_API_KEY=<PASTE_API_KEY_HERE>
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
chmod o+w "$LOCAL_NIM_CACHE"
podman run -it --rm \
    --device nvidia.com/gpu=all \
    --shm-size=16GB \
    -e NGC_API_KEY=$NGC_API_KEY \
    -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \
    -e NIM_RELAX_MEM_CONSTRAINTS=1 \
    -u $(id -u) \
    -p 8000:8000 \
    nvcr.io/nim/baidu/paddleocr:1.1.0-rtx

The first few (depending on number of GPUs) inference requests may take longer than subsequent ones. This is due to the model being loaded into memory and initialized for the first time.

Step 3
Test the NIM

You can now make a local API call by opening another Distro instance and using this curl command:

HOSTNAME="localhost"
SERVICE_PORT=8000
curl -X "POST" \
  "http://${HOSTNAME}:${SERVICE_PORT}/v1/infer" \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
        "input": [
          {
            "type": "image_url",
            "url": "data:image/png;base64,<BASE64_ENCODED_IMAGE>"
          },
          {
            "type": "image_url",
            "url": "data:image/png;base64,<BASE64_ENCODED_IMAGE>"
          }
        ]
      }'

For more details on getting started with this NIM, visit the NVIDIA NIM Docs.