felipebandeira
/

donutlicenses1

Image-Text-to-Text

vision-encoder-decoder

Inference Endpoints

Model card Files Files and versions Community

felipebandeira commited on Jul 31, 2023

Commit

86fb871

•

1 Parent(s): 68a5a02

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -1,3 +1,4 @@
 ---
 license: mit
 ---

 ---
 license: mit
 ---
+This is a (wrongly named) implementation of a fine-tuned Donut for EU driver licenses. The model was fine tuned using a dataset of 1k synthetic licenses