Average Normalized Levenshtein Similarity (ANLS) for evaluating text similarity, especially in OCR and document understanding tasks. Version 0.0.2, released occasionally.
pip install anlsNo compatibility data collected yet for this library.
Verified import paths — ran on the pinned version, not inferred.
Compute ANLS between two strings.
Ensure both inputs are str.
Consider implementing custom Levenshtein or use rapidfuzz.
pip install anls
Use anls_score(reference, prediction) with exactly two strings.