Welcome to KaMI App!
KaMI stands for Kraken Model Inspector. It evaluates the success of a transcription task (HTR, OCR) comparing a correct transcription (reference) and a prediction.
Metrics dashboard
Show versus text
REFERENCE
COMPARAISON
PREDICTION
Understand the metrics
- Levensthein Distance (Char.): Levenshtein distance at character level.
- Levensthein Distance (Words): Levenshtein distance at word level.
- Hamming Distance: a score if the strings' lengths match but their content is different; Ø if the strings' lengths don't match.
- WER: Word Error Rate, proportion of words bearing at least one recognition error.
- CER: Character Error Rate, proportion of characters erroneously transcribed.
- Wacc: Word Accuracy, proportion of words bearing no recognition error.
- Match Error Rate: metric borrowed from Speech Recognition
- Char. Information Lost: metric borrowed from Speech Recognition
- Char. Information Preserve: metric borrowed from Speech Recognition
- Hits: number of characters identical between the reference and the prediction.
- Substitutions: number of substitutions (a character replaced by another) necessary to make the prediction match the reference
- Deletions: number of deletions (a character is removed) necessary to make the prediction match the reference
- Insertions: number of insertions (a character is added) necessary to make the prediction match the reference