agomberto
/

trocr-large-handwritten-fr

vision-encoder-decoder

image-text-to-text

Inference Endpoints

Model card Files Files and versions Community

agomberto commited on Jul 20, 2023

Commit

b86a3bb

•

1 Parent(s): e75e7f4

:memo: new. model metrics update

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -58,16 +58,16 @@ We used heuristic parameters without separate hyperparameter tuning.
 ## Metrics
 For the dev set we got those results
-- size of the set: 700 examples from French Census  / 1200 from our own dataset
-- CER: 0.0636
-- WER: 0.1823
-- Loss: 0.6386
 For the test set we got those results
 - size of the set: 730 examples from French Census  / 950 from our own dataset
-- CER: 0.09012
-- WER: 0.20446
-- Loss: 0.8547
 ### How to use

 ## Metrics
 For the dev set we got those results
+- size of the set: 700 examples from French Census  / 1600 from our own dataset
+- CER: 0.0575
+- WER: 0.1651
+- Loss: 0.5768
 For the test set we got those results
 - size of the set: 730 examples from French Census  / 950 from our own dataset
+- CER: 0.09417
+- WER: 0.23485
+- Loss: 0.8700
 ### How to use