>>> wer = datasets.load_metric("wer")
>>> wer_score = wer.compute(predictions=predictions, references=references)
>>> print(wer_score)
0.5
"""
class AddSpacesToPunctuation(tr.AbstractTransform):
def process_string(self, s: str):
return re.sub("(['.,:;?!&])", r" \1 ", s)
_transform = tr.Compose(
[
AddSpacesToPunctuation(),
tr.RemoveMultipleSpaces(),
tr.Strip(),
tr.SentencesToListOfWords(),
tr.RemoveEmptyStrings(),
]
)
class WER_punctuation(datasets.Metric):
def _info(self):
return datasets.MetricInfo(
description=_DESCRIPTION,
citation=_CITATION,
inputs_description=_KWARGS_DESCRIPTION,
features=datasets.Features(
{
def __init__(self, sentence_delimiter: str = " "):
self.sentence_delimiter = sentence_delimiter
def process_string(self, s: str):
return list(s)
def process_list(self, inp: List[str]):
chars = []
for sent_idx, sentence in enumerate(inp):
chars.extend(self.process_string(sentence))
if self.sentence_delimiter is not None and self.sentence_delimiter != "" and sent_idx < len(inp) - 1:
chars.append(self.sentence_delimiter)
return chars
cer_transform = tr.Compose(
[tr.RemoveMultipleSpaces(), tr.Strip(), SentencesToListOfCharacters(SENTENCE_DELIMITER)]
)
else:
cer_transform = tr.Compose(
[
tr.RemoveMultipleSpaces(),
tr.Strip(),
tr.ReduceToSingleSentence(SENTENCE_DELIMITER),
tr.ReduceToListOfListOfChars(),
]
)
_CITATION = """\
@inproceedings{inproceedings,
author = {Morris, Andrew and Maier, Viktoria and Green, Phil},
