{% extends "headerfooter.html"%} {% block body %} {% include 'partials/kami_logo_animation.svg' %} 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. Do more with KaMI-lib colab Reference (Maximum characters: 7000) You have characters left. Prediction (Maximum characters: 7000) You have characters left. Text preprocessing options Ignore all digits Ignore text case (all in lower case) Ignore the punctuation Ignore diacritical signs Features available Create versus text Compare Metrics dashboard Export to CSV Understand the metrics Show versus text Show/Hide edit operations: Exact match Insertion Deletion/substition 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 {% endblock %} {% block script %} {% endblock %}
KaMI stands for Kraken Model Inspector. It evaluates the success of a transcription task (HTR, OCR) comparing a correct transcription (reference) and a prediction.
Do more with KaMI-lib colab
Text preprocessing options
Features available