AraCLIP

Cross-Lingual Learning for Effective Arabic Image Retrieval

Live Demo · Pre-trained Models · Report Bug

Overview

Demo

A live demonstration of multilingual Text-Image retrieval using M-CLIP can be found here!

Setting Up the Environment

To set up the environment, please use the environment.yaml file. This file contains all the necessary dependencies.

Setting Up the Environment

To create the conda environment using the environment.yaml file, run the following command:

conda env create -f environment.yaml

Pre-trained Models

Every text encoder is a Arabic-Clip Huggingface Organization available transformer, with an additional linear layer on top to be downloaded.

Acknowledgements

• Multilingual-CLIP
• Stability.ai for providing much appreciated compute during training.
• CLIP
• OpenAI
• Huggingface
• Best Readme Template
• "Two Cats" Image by pl1602

License

Distributed under the MIT License. See LICENSE for more information.