File size: 4,056 Bytes
2493d72 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
'''
Cleaners are transformations that run over the input text at both training and eval time.
Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
hyperparameter. Some cleaners are English-specific. You'll typically want to use:
1. "english_cleaners" for English text
2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
the Unidecode library (https://pypi.python.org/pypi/Unidecode)
3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
the symbols in symbols.py to match your data).
'''
import re
from unidecode import unidecode
from .number_norm import normalize_numbers
from .abbreviations import abbreviations_en, abbreviations_fr
from .time import expand_time_english
# Regular expression matching whitespace:
_whitespace_re = re.compile(r'\s+')
def expand_abbreviations(text, lang='en'):
if lang == 'en':
_abbreviations = abbreviations_en
elif lang == 'fr':
_abbreviations = abbreviations_fr
for regex, replacement in _abbreviations:
text = re.sub(regex, replacement, text)
return text
def expand_numbers(text):
return normalize_numbers(text)
def lowercase(text):
return text.lower()
def collapse_whitespace(text):
return re.sub(_whitespace_re, ' ', text).strip()
def convert_to_ascii(text):
return unidecode(text)
def remove_aux_symbols(text):
text = re.sub(r'[\<\>\(\)\[\]\"]+', '', text)
return text
def replace_symbols(text, lang='en'):
text = text.replace(';', ',')
text = text.replace('-', ' ')
text = text.replace(':', ',')
if lang == 'en':
text = text.replace('&', ' and ')
elif lang == 'fr':
text = text.replace('&', ' et ')
elif lang == 'pt':
text = text.replace('&', ' e ')
return text
def basic_cleaners(text):
'''Basic pipeline that lowercases and collapses whitespace without transliteration.'''
text = lowercase(text)
text = collapse_whitespace(text)
return text
def transliteration_cleaners(text):
'''Pipeline for non-English text that transliterates to ASCII.'''
text = convert_to_ascii(text)
text = lowercase(text)
text = collapse_whitespace(text)
return text
def basic_german_cleaners(text):
'''Pipeline for German text'''
text = lowercase(text)
text = collapse_whitespace(text)
return text
# TODO: elaborate it
def basic_turkish_cleaners(text):
'''Pipeline for Turkish text'''
text = text.replace("I", "ı")
text = lowercase(text)
text = collapse_whitespace(text)
return text
def english_cleaners(text):
'''Pipeline for English text, including number and abbreviation expansion.'''
text = convert_to_ascii(text)
text = lowercase(text)
text = expand_time_english(text)
text = expand_numbers(text)
text = expand_abbreviations(text)
text = replace_symbols(text)
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def french_cleaners(text):
'''Pipeline for French text. There is no need to expand numbers, phonemizer already does that'''
text = lowercase(text)
text = expand_abbreviations(text, lang='fr')
text = replace_symbols(text, lang='fr')
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def portuguese_cleaners(text):
'''Basic pipeline for Portuguese text. There is no need to expand abbreviation and
numbers, phonemizer already does that'''
text = lowercase(text)
text = replace_symbols(text, lang='pt')
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def phoneme_cleaners(text):
'''Pipeline for phonemes mode, including number and abbreviation expansion.'''
text = expand_numbers(text)
text = convert_to_ascii(text)
text = expand_abbreviations(text)
text = replace_symbols(text)
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
|