vak.metrics.distance.distance.CharacterErrorRate#

class vak.metrics.distance.distance.CharacterErrorRate[source]#

Bases: object

Levenshtein edit distance normalized by length of true sequence. Also known as word error distance; here applied to other vocalizations in addition to speech.

Parameters:

  • y_pred (str) – predicted labels for a series of songbird syllables

  • y_true (str) – ground truth labels for a series of songbird syllables

Return type:

Levenshtein distance(y_pred, y_true) / len(y_true)

__init__()[source]#

Methods

__init__()