Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
katanaml
/
donut-demo
like
3
Image-to-Text
Transformers
PyTorch
naver-clova-ix/cord-v2
vision-encoder-decoder
Inference Endpoints
License:
mit
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
Edit model card
Donut model finetuned with CORD dataset. Mean accuracy: 0.901198895445646
Katana ML
Sparrow GitHub
Downloads last month
21
Inference API
Image-to-Text
Drag image file here or click to browse from your device
Browse for image
This model can be loaded on Inference API (serverless).
JSON Output
Maximize
Dataset used to train
katanaml/donut-demo
naver-clova-ix/cord-v2
Viewer
β’
Updated
Jul 19, 2022
β’
1k
β’
13.9k
β’
51
Spaces using
katanaml/donut-demo
3
π
irfank/katanaml-donut-demo-3
π¨
matthartman/katanaml-donut-demo
π₯
irfank/katanaml-donut-demo