Fact · Speech recognition
5.06percent
On the same typewritten historical records, the OCR output had a word error rate of 5.06 percent.
Checked against its source on October 17, 2026
In the source's own words
“OCR achieved a Character Error Rate (CER) of 1.08% and a Word Error Rate (WER) of 5.06%”
Enriching Historical Records: An OCR and AI-Driven Approach for Database Integration, Zahra Abedi, arXiv, 2025, Abstract.
Open the original- What it measures
- The same OCR output, scored at the word level. A wrong character inside a word makes the whole word count as an error in WER, which is why WER is higher here.
- What it does not show
- The comparison is between two measures on the same output. The gap between the two measures is specific to this collection.