Try the Model

Use the widget below to experiment with PaliGemma Optical Character Recognition. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

You can use the set of PaliGemma weights trained on the OCRVQA dataset for performing OCR on images.

See the official PaliGemma model card for more information about PaliGemma.

PaliGemma Optical Character Recognition License

PaliGemma Optical Character Recognition

is licensed under a

license.

Performance

Deploy a PaliGemma Optical Character Recognition API

You can use Roboflow Inference to deploy a

PaliGemma Optical Character Recognition

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with PaliGemma Optical Character Recognition

You can automatically label a dataset using PaliGemma Optical Character Recognition with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use PaliGemma Optical Character Recognition to train a computer vision model.

No items found.