agomberto
/

trocr-large-handwritten-fr

vision-encoder-decoder

image-text-to-text

Inference Endpoints

Model card Files Files and versions Community

agomberto commited on Jun 9, 2023

Commit

df4eade

·

1 Parent(s): e476c37

:memo: update metrics

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -56,13 +56,13 @@ We used heuristic parameters without separate hyperparameter tuning.
 For the dev set we got those results
 - size of the set: 700 examples from French Census  / 950 from our own dataset
-- CER: 0.06
-- WER: 0.16
 For the test set we got those results
 - size of the set: 730 examples from French Census  / 950 from our own dataset
-- CER: 0.6
-- WER: 0.14
 ### How to use

 For the dev set we got those results
 - size of the set: 700 examples from French Census  / 950 from our own dataset
+- CER: 0.0641
+- WER: 0.1566
 For the test set we got those results
 - size of the set: 730 examples from French Census  / 950 from our own dataset
+- CER: 0.0573
+- WER: 0.1402
 ### How to use