AI engineering glossary · Evaluation metrics
What is CER (character error rate)?
Character error rate (also called CER): The same edit-distance idea as word error rate applied to characters: (substitutions + deletions + insertions) / number of reference characters. It suits handwriting and OCR tasks and languages without clear word boundaries, and it gives partial credit for near-miss words.
Character error rate: an example
An OCR system reads 'Bengaluru' as 'Bengalura'; that is 1 substitution over 9 characters, so CER = 1 / 9, about 11%.
Related terms
More Evaluation metrics terms
- chrF
- CIDEr
- Cohen's kappa
- Confusion matrix
- Continuous ranked probability score
- Cost matrix
- Cranfield paradigm
- Cumulative gains chart
Where you learn it
Character error rate is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.