Hugging Face's logo

katanaml
/
donut-demo

Image-to-Text
Transformers
PyTorch
vision-encoder-decoder
Inference Endpoints
Model card Files Community
1
Edit model card

Donut model finetuned with CORD dataset. Mean accuracy: 0.901198895445646

Downloads last month
21
Inference API
Image-to-Text
This model can be loaded on Inference API (serverless).

Dataset used to train katanaml/donut-demo

Spaces using katanaml/donut-demo 3