Oliverfelt

icon indicating an email [email protected]

icon location Rio de Janeiro, RJ icon location Computer Engineering, passionate about networking, challenges and experiences, who seeks to apply gained knowledge.

Results 2 comments of Oliverfelt

CER Normalization

Hi @lvwerra! My point is that when CER metric is above 1.0, like in this example: reference: 2.49 prediction: 749.00 cer: 1.25 substitute= 1 delete = 1 insert = 3...

CER Normalization

I think this way could work well! I'm fowarding the link with the CER normalization content and a image with it's explanation. https://towardsdatascience.com/evaluating-ocr-output-quality-with-character-error-rate-cer-and-word-error-rate-wer-853175297510#5aec ![image](https://user-images.githubusercontent.com/36710164/180999337-c7a6695a-9bd7-4dbc-9419-84624070ead4.png)