---
language: ar
datasets: flickr8k
---

# AraBERT32-Flickr8k

AraBERT32-Flickr8k is an image captioning model initialized on [bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) and fine-tuned on the Arabic Flickr8k dataset with the [OSCAR](https://github.com/microsoft/Oscar) learning method.