Downloads · 30 days
68
1% of all-time downloads
vit-roberta-fa-image-captioning-flickr30k
hezarai/vit-roberta-fa-image-captioning-flickr30k
vit-roberta-fa-image-captioning-flickr30k is a image-to-text model from hezarai. Use it when you need a caption or text from an image. It is set up for hezar.
A Persian image captioning model constructed from a ViT + RoBERTa architecture trained on flickr30k-fa (created by Sajjad Ayoubi). The encoder (ViT) was initialized from https://huggingface.co/google/vit-base-patch16-…
All-time downloads
5.1K
Public
Repo size
933 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt933 MB · 100%
At a glance
- Task
- Image-to-Text
- Library
- hezar
- Access
- Public
- Created
- Sep 29, 2023
- Updated
- Nov 14, 2024
- SHA
- e6018532
Datasets
Model card
From the Hugging Face model README
A Persian image captioning model constructed from a ViT + RoBERTa architecture trained on flickr30k-fa (created by Sajjad Ayoubi). The encoder (ViT) was initialized from https://huggingface.co/google/vit-base-patch16-224 and the decoder (RoBERTa) was initialized from https://huggingface.co/HooshvareLab/roberta-fa-zwnj-base .
Usage
pip install hezar
from hezar.models import Model
model = Model.load("hezarai/vit-roberta-fa-image-captioning-flickr30k")
captions = model.predict("example_image.jpg")
print(captions)
- Task
- Image-to-Text
- Library
- hezar
- Languages
- fa
- Created
- Sep 29, 2023
- Updated
- Nov 14, 2024