zhongren2
/

donut-demo

vision-encoder-decoder

Model card Files Files and versions

donut-demo / README.md

zhongren2's picture

Create README.md

5b4d1da almost 2 years ago

|

history blame contribute delete

103 Bytes

metadata

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