def _calc_metrics(self, ground_truth, hypothesis):
transformation = jiwer.Compose([
jiwer.ToLowerCase(),
jiwer.RemoveMultipleSpaces(),
jiwer.RemoveWhiteSpace(replace_by_space=" "),
jiwer.SentencesToListOfWords(word_delimiter=" ")
])
mer = jiwer.mer(ground_truth,
hypothesis,
truth_transform=transformation,
hypothesis_transform=transformation)
wer = jiwer.wer(ground_truth,
hypothesis,
truth_transform=transformation,
hypothesis_transform=transformation)
wil = jiwer.wil(ground_truth,
hypothesis,
truth_transform=transformation,
hypothesis_transform=transformation)
wip = jiwer.wip(ground_truth,
hypothesis,
truth_transform=transformation,
hypothesis_transform=transformation)
return mer, wer, wil, wip
def _str_clean(input_string: str) -> str:
"""
Use jiwer's
"""
transformation = jiwer.Compose([
jiwer.ToLowerCase(),
jiwer.RemoveMultipleSpaces(),
jiwer.RemoveWhiteSpace(replace_by_space=True),
jiwer.SentencesToListOfWords(word_delimiter=" ")
])
return transformation(input_string)
def sentence_wer(reference: str, prediction: str):
transformation = jiwer.Compose([
jiwer.RemoveMultipleSpaces(),
jiwer.RemovePunctuation(),
jiwer.Strip(),
jiwer.ToLowerCase(),
jiwer.ExpandCommonEnglishContractions(),
jiwer.RemoveWhiteSpace(replace_by_space=True),
jiwer.SentencesToListOfWords(),
jiwer.RemoveEmptyStrings(),
])
return jiwer.wer(reference.strip(),
prediction.strip(),
truth_transform=transformation,
hypothesis_transform=transformation)
def normalize_sentence(sentence):
"""Normalize sentence"""
# Convert all characters to upper.
sentence = sentence.upper()
# Delete punctuations.
sentence = jiwer.RemovePunctuation()(sentence)
# Remove \n, \t, \r, \x0c.
sentence = jiwer.RemoveWhiteSpace(replace_by_space=True)(sentence)
# Remove multiple spaces.
sentence = jiwer.RemoveMultipleSpaces()(sentence)
# Remove white space in two end of string.
sentence = jiwer.Strip()(sentence)
# Convert all characters to upper.
sentence = sentence.upper()
return sentence
def analyze():
try:
req_data = request.get_json()
compose_rule_set = []
if req_data.get('to_lower_case', False) == True:
compose_rule_set.append(jiwer.ToLowerCase())
if req_data.get('strip_punctuation', False) == True:
compose_rule_set.append(jiwer.RemovePunctuation())
if req_data.get('strip_words', False) == True:
compose_rule_set.append(jiwer.Strip())
if req_data.get('strip_multi_space', False) == True:
compose_rule_set.append(jiwer.RemoveMultipleSpaces())
word_excepts = req_data.get('t_words', '')
if word_excepts != '':
words = [a.strip() for a in word_excepts.split(",")]
compose_rule_set.append(jiwer.RemoveSpecificWords(words))
compose_rule_set.append(
jiwer.RemoveWhiteSpace(
replace_by_space=req_data.get('replace_whitespace', False)))
transformation = jiwer.Compose(compose_rule_set)
measures = jiwer.compute_measures(req_data.get('s_truth', ""),
req_data.get('s_hypo', ""),
truth_transform=transformation,
hypothesis_transform=transformation)
return jsonify({
"wer": measures['wer'],
"mer": measures['mer'],
"wil": measures['wil']
})
except:
return jsonify("API endpoint Error")
def metric(ref_trans, asr_trans, lang):
if lang == "en":
transformation = jiwer.Compose([
jiwer.Strip(),
jiwer.ToLowerCase(),
jiwer.RemoveWhiteSpace(replace_by_space=True),
jiwer.RemoveMultipleSpaces(),
jiwer.SentencesToListOfWords(word_delimiter=" "),
jiwer.RemoveEmptyStrings(),
jiwer.RemovePunctuation(),
])
wer = jiwer.wer(
ref_trans,
asr_trans,
truth_transform=transformation,
hypothesis_transform=transformation,
)
elif lang == "cn":
del_symblos = re.compile(r"[^\u4e00-\u9fa5]+")
for idx in range(len(asr_trans)):
sentence = re.sub(del_symblos, "", asr_trans[idx])
sentence = list(sentence)
sentence = " ".join(sentence)
asr_trans[idx] = sentence
sentence = re.sub(del_symblos, "", ref_trans[idx])
sentence = list(sentence)
sentence = " ".join(sentence)
ref_trans[idx] = sentence
asr_valid = set(asr_trans)
assert len(asr_valid) == len(asr_trans)
wer = jiwer.wer(ref_trans, asr_trans)
else:
raise ("Args error!")
return wer
tstart = next_sub.start.hours * 3600 + next_sub.start.minutes * 60 + next_sub.start.seconds + next_sub.start.milliseconds / 1000
if (tstart - end) > 0.5:
srt.push(next_sub)
break
end = next_sub.end.hours * 3600 + next_sub.end.minutes * 60 + next_sub.end.seconds + next_sub.end.milliseconds / 1000
ground_truth = ground_truth + " " + next_sub.text_without_tags
hypothesis = kd.query_text(start, end)
else:
break
kd.mark_words(start, end)
transformation = jiwer.Compose([
jiwer.ToLowerCase(),
jiwer.RemoveMultipleSpaces(),
jiwer.RemoveWhiteSpace(replace_by_space=True),
jiwer.SentencesToListOfWords(),
jiwer.RemovePunctuation(),
jiwer.RemoveEmptyStrings(),
jiwer.SubstituteRegexes({r"ё": r"е"})
])
gt = transformation([ground_truth])
hp = transformation([hypothesis])
gt, hp = replace_pairs(gt, hp)
hp, gt = replace_pairs(hp, gt)
wer(gt, hp)
r = jiwer.compute_measures(
gt,
text = text.replace(p, ' ')
return text
def RemovePunctuation(replace_by_space=False):
if not replace_by_space:
return jiwer.RemovePunctuation()
return replace_punctuations_by_space
transformation = jiwer.Compose([
jiwer.ToLowerCase(),
RemovePunctuation(replace_by_space=False),
jiwer.RemoveMultipleSpaces(),
jiwer.Strip(),
jiwer.RemoveEmptyStrings(),
jiwer.SentencesToListOfWords(),
jiwer.RemoveWhiteSpace(replace_by_space=False),
jiwer.RemoveEmptyStrings(),
])
def compute_avg_wer(ground_truth, hypothesis):
assert len(ground_truth) == len(hypothesis)
wer_sum = 0
for gt, h in zip(ground_truth, hypothesis):
wer_score = jiwer.wer(
gt,
h,
truth_transform=transformation,
hypothesis_transform=transformation
)
wer_sum += wer_score