Modular and extensible framework for Arabic Visual Question Answering (VQA) using state-of-the-art pretrained models for image captioning and question answering.
-
Updated
Jan 20, 2025 - Jupyter Notebook
Modular and extensible framework for Arabic Visual Question Answering (VQA) using state-of-the-art pretrained models for image captioning and question answering.
Fine‑tune aragpt2‑base to generate Arabic quizzes from any document (PDF, DOCX, image, audio). NLP final project.
Add a description, image, and links to the aragpt2 topic page so that developers can more easily learn about it.
To associate your repository with the aragpt2 topic, visit your repo's landing page and select "manage topics."