donut-base

naver-clova-ix/donut-base

Image to TexttransformersLicense: mit
Tracked by OpenModelStats since September 28, 2026View on Hugging Face ↗
Downloads 30D
76.6K
Total downloads
4M
Gained 7D
+10.9K(increase)
0.3%(up) vs baseline
Gained 30D
—
Likes
255
+1 in 7D
Rank · tracked models
#3,078
14(up 14 places)this week
Parameters
—
Last source update
Aug 13, 2022
Momentum
78.3
  • donut-base gained 10.9K downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

donut-base is a image to text model published by naver-clova-ix. OpenModelStats has tracked the model since Sep 28, 2026, most recently observing it Oct 5, 2026.

Published
Jul 19, 2022
Last updated
Aug 13, 2022
Library
transformers
License
mit
Task
Image to Text
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
1,551
transformerspytorchvision-encoder-decoderimage-text-to-textdonutimage-to-textvisionarxiv:2111.15664license:mitendpoints_compatibleregion:us

Similar models

Models similar to donut-base
ModelDL 30D
GLM-OCRzai-org1.8M
blip-image-captioning-baseSalesforce1.5M
manga-ocr-basekha-white1.1M
blip-image-captioning-largeSalesforce583.3K
PP-OCRv5_server_detPaddlePaddle522.6K
UVDocPaddlePaddle468.2K
naver-clova-ix/donut-base — Downloads, Growth & Stats | OpenModelStats