def test_norm(self, test_input, expected):
pred = normalize(test_input, verbose=False)
assert pred == expected
def split_text(
in_file: str,
out_file: str,
vocabulary: List[str] = None,
language='eng',
remove_brackets=True,
do_lower_case=True,
min_length=0,
max_length=100,
additional_split_symbols=None,
use_nemo_normalization=False,
):
"""
Breaks down the in_file roughly into sentences. Each sentence will be on a separate line.
Written form of the numbers will be converted to its spoken equivalent, OOV punctuation will be removed.
Args:
in_file: path to original transcript
out_file: path to the output file
vocabulary: ASR model vocabulary
language: text language
remove_brackets: Set to True if square [] and curly {} brackets should be removed from text.
Text in square/curly brackets often contains inaudible fragments like notes or translations
do_lower_case: flag that determines whether to apply lower case to the in_file text
min_length: Min number of chars of the text segment for alignment. Short segments will be combined to be
at least min_length (not recommended for multi speaker data).
max_length: Max number of chars of the text segment for alignment
additional_split_symbols: Additional symbols to use for sentence split if eos sentence split resulted in
segments longer than --max_length
use_nemo_normalization: Set to True to use NeMo normalization tool to convert numbers from written to spoken
format. Normalization using num2words will be applied afterwards to make sure there are no numbers present
in the text, otherwise they will be replaced with a space and that could deteriorate segmentation results.
"""
print(f'Splitting text in {in_file} into sentences.')
with open(in_file, "r") as f:
transcript = f.read()
# remove some symbols for better split into sentences
transcript = (transcript.replace("\n", " ").replace("\t", " ").replace(
"…",
"...").replace("\\",
" ").replace("--",
" -- ").replace(". . .",
"...").replace("‘", "’"))
# remove extra space
transcript = re.sub(r' +', ' ', transcript)
transcript = re.sub(r'(\.+)', '. ', transcript)
if remove_brackets:
transcript = re.sub(r'(\[.*?\])', ' ', transcript)
# remove text in curly brackets
transcript = re.sub(r'(\{.*?\})', ' ', transcript)
lower_case_unicode = ''
upper_case_unicode = ''
if language == 'ru':
lower_case_unicode = '\u0430-\u04FF'
upper_case_unicode = '\u0410-\u042F'
elif language not in ['ru', 'eng']:
print(
f'Consider using {language} unicode letters for better sentence split.'
)
# remove space in the middle of the lower case abbreviation to avoid splitting into separate sentences
matches = re.findall(
r'[a-z' + lower_case_unicode + ']\.\s[a-z' + lower_case_unicode +
']\.', transcript)
for match in matches:
transcript = transcript.replace(match, match.replace('. ', '.'))
# find phrases in quotes
with_quotes = re.finditer(r'“[A-Za-z ?]+.*?”', transcript)
sentences = []
last_idx = 0
for m in with_quotes:
match = m.group()
match_idx = m.start()
if last_idx < match_idx:
sentences.append(transcript[last_idx:match_idx])
sentences.append(match)
last_idx = m.end()
sentences.append(transcript[last_idx:])
sentences = [s.strip() for s in sentences if s.strip()]
# Read and split transcript by utterance (roughly, sentences)
split_pattern = f"(?<!\w\.\w.)(?<![A-Z{upper_case_unicode}][a-z{lower_case_unicode}]\.)(?<![A-Z{upper_case_unicode}]\.)(?<=\.|\?|\!|\.”|\?”\!”)\s"
new_sentences = []
for sent in sentences:
new_sentences.extend(regex.split(split_pattern, sent))
sentences = [s.strip() for s in new_sentences if s.strip()]
def additional_split(sentences, split_on_symbols, max_length):
if len(split_on_symbols) == 0:
return sentences
split_on_symbols = split_on_symbols.split('|')
def _split(sentences, symbol, max_length):
result = []
for s in sentences:
if len(s) <= max_length:
result.append(s)
else:
result.extend(s.split(symbol))
return result
another_sent_split = []
for sent in sentences:
split_sent = [sent]
for sym in split_on_symbols:
split_sent = _split(split_sent, sym, max_length)
another_sent_split.extend(split_sent)
sentences = [s.strip() for s in another_sent_split if s.strip()]
return sentences
sentences = additional_split(sentences, additional_split_symbols,
max_length)
# check to make sure there will be no utterances for segmentation with only OOV symbols
no_space_voc = set(vocabulary)
no_space_voc.remove(' ')
sentences = [
s for s in sentences if len(no_space_voc.intersection(set(s))) > 0
]
if min_length > 0:
sentences_comb = []
sentences_comb.append(sentences[0])
# combines short sentence
for i in range(1, len(sentences)):
if len(sentences_comb[-1]) < min_length or len(
sentences[i]) < min_length:
sentences_comb[-1] += ' ' + sentences[i].strip()
else:
sentences_comb.append(sentences[i].strip())
sentences = "\n".join([s.strip() for s in sentences_comb if s.strip()])
else:
sentences = "\n".join([s.strip() for s in sentences if s.strip()])
# save split text with original punctuation and case
out_dir, out_file_name = os.path.split(out_file)
with open(os.path.join(out_dir, out_file_name[:-4] + '_with_punct.txt'),
"w") as f:
f.write(sentences)
# substitute common abbreviations before applying lower case
if language == 'ru':
for k, v in RU_ABBREVIATIONS.items():
sentences = sentences.replace(k, v)
if do_lower_case:
sentences = sentences.lower()
if language == 'ru':
# replace Latin characters with Russian
for k, v in LATIN_TO_RU.items():
sentences = sentences.replace(k, v)
if language == 'eng' and use_nemo_normalization:
print('Using NeMo normalization tool...')
sentences = normalize(sentences, verbose=False)
# replace numbers with num2words
try:
p = re.compile("\d+")
new_text = ''
match_end = 0
for i, m in enumerate(p.finditer(sentences)):
match = m.group()
match_start = m.start()
if i == 0:
new_text = sentences[:match_start]
else:
new_text += sentences[match_end:match_start]
match_end = m.end()
new_text += sentences[match_start:match_end].replace(
match, num2words(match, lang=language))
new_text += sentences[match_end:]
sentences = new_text
except NotImplementedError:
print(
f'{language} might be missing in "num2words" package. Add required language to the choices for the'
f'--language argument.')
raise
# remove all OOV symbols
all_symbols = set(sentences)
symbols_to_remove = ''.join(
all_symbols.difference(set(vocabulary + ['\n'])))
sentences = sentences.translate(''.maketrans(symbols_to_remove,
len(symbols_to_remove) * ' '))
# remove extra space
sentences = re.sub(r' +', ' ', sentences)
with open(out_file, "w") as f:
f.write(sentences)