File size: 3,494 Bytes
e8bdc47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
""" from https://github.com/keithito/tacotron """

'''
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 phonemizer import phonemize


# Regular expression matching whitespace:
_whitespace_re = re.compile(r'\s+')

# List of (regular expression, replacement) pairs for abbreviations:
_abbreviations = [(re.compile('\\b%s\\.' % x[0], re.IGNORECASE), x[1]) for x in [
  ('mrs', 'misess'),
  ('mr', 'mister'),
  ('dr', 'doctor'),
  ('st', 'saint'),
  ('co', 'company'),
  ('jr', 'junior'),
  ('maj', 'major'),
  ('gen', 'general'),
  ('drs', 'doctors'),
  ('rev', 'reverend'),
  ('lt', 'lieutenant'),
  ('hon', 'honorable'),
  ('sgt', 'sergeant'),
  ('capt', 'captain'),
  ('esq', 'esquire'),
  ('ltd', 'limited'),
  ('col', 'colonel'),
  ('ft', 'fort'),
]]


def expand_abbreviations(text):
  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)


def convert_to_ascii(text):
  return unidecode(text)

def basic_cleaners(text):
  '''Basic pipeline that lowercases and collapses whitespace without transliteration.'''
  #text = lowercase(text)
  text = collapse_whitespace(text)
  text = replace_quote(text)
  text = remove_special_characters(text)
  text = remove_hyphen_at_start(text)
  return text

def replace_quote(text):
    return text.replace('’', "'")

def remove_special_characters(text):
    # Define the characters to remove
    characters_to_remove = ['«', '»']
    # Remove the characters from the text
    for char in characters_to_remove:
        text = text.replace(char, '')
    return text

def remove_hyphen_at_start(text):
    # Check if the text starts with '-'
    if text.startswith('-'):
        # Remove the hyphen at the start
        text = text[1:].lstrip()
    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 english_cleaners(text):
  '''Pipeline for English text, including abbreviation expansion.'''
  text = convert_to_ascii(text)
  text = lowercase(text)
  text = expand_abbreviations(text)
  phonemes = phonemize(text, language='en-us', backend='espeak', strip=True)
  phonemes = collapse_whitespace(phonemes)
  return phonemes


def english_cleaners2(text):
  '''Pipeline for English text, including abbreviation expansion. + punctuation + stress'''
  text = convert_to_ascii(text)
  text = lowercase(text)
  text = expand_abbreviations(text)
  phonemes = phonemize(text, language='en-us', backend='espeak', strip=True, preserve_punctuation=True, with_stress=True)
  phonemes = collapse_whitespace(phonemes)
  return phonemes