Metric¶
Metric¶
-
class
openspeech.metrics.
CharacterErrorRate
(tokenizer)[source]¶ Computes the Character Error Rate, defined as the edit distance between the two provided sentences after tokenizing to characters.
-
metric
(s1: str, s2: str) → Tuple[float, int][source]¶ Computes the Character Error Rate, defined as the edit distance between the two provided sentences after tokenizing to characters.
- Args: s1, s2
s1 (string): space-separated sentence s2 (string): space-separated sentence
- Returns: dist, length
dist: distance between target & y_hat
length: length of target sequence
-
-
class
openspeech.metrics.
ErrorRate
(tokenizer)[source]¶ Provides inteface of error rate calcuation.
Note
Do not use this class directly, use one of the sub classes.
-
class
openspeech.metrics.
WordErrorRate
(tokenizer)[source]¶ Computes the Word Error Rate, defined as the edit distance between the two provided sentences after tokenizing to words.
-
metric
(s1: str, s2: str) → Tuple[float, int][source]¶ Computes the Word Error Rate, defined as the edit distance between the two provided sentences after tokenizing to words.
- Args: s1, s2
s1 (string): space-separated sentence s2 (string): space-separated sentence
- Returns: dist, length
dist: distance between target & y_hat
length: length of target sequence
-