katanaml
/

donut-demo

vision-encoder-decoder

image-text-to-text

Inference Endpoints

Model card Files Files and versions Community

donut-demo / README.md

katanaml's picture

Update README.md

7213e17 almost 2 years ago

|

270 Bytes

metadata

license: mit
datasets:
  - naver-clova-ix/cord-v2
metrics:
  - accuracy
pipeline_tag: image-to-text

Donut model finetuned with CORD dataset. Mean accuracy: 0.901198895445646