Upload 4 files

text/cleaners.py

@@ -0,0 +1,90 @@
+""" 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 .numbers import normalize_numbers
+
+
+# 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)
+  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 number and abbreviation expansion.'''
+  text = convert_to_ascii(text)
+  text = lowercase(text)
+  text = expand_numbers(text)
+  text = expand_abbreviations(text)
+  text = collapse_whitespace(text)
+  return text

text/cmudict.py

@@ -0,0 +1,65 @@
+""" from https://github.com/keithito/tacotron """
+
+import re
+
+
+valid_symbols = [
+  'AA', 'AA0', 'AA1', 'AA2', 'AE', 'AE0', 'AE1', 'AE2', 'AH', 'AH0', 'AH1', 'AH2',
+  'AO', 'AO0', 'AO1', 'AO2', 'AW', 'AW0', 'AW1', 'AW2', 'AY', 'AY0', 'AY1', 'AY2',
+  'B', 'CH', 'D', 'DH', 'EH', 'EH0', 'EH1', 'EH2', 'ER', 'ER0', 'ER1', 'ER2', 'EY',
+  'EY0', 'EY1', 'EY2', 'F', 'G', 'HH', 'IH', 'IH0', 'IH1', 'IH2', 'IY', 'IY0', 'IY1',
+  'IY2', 'JH', 'K', 'L', 'M', 'N', 'NG', 'OW', 'OW0', 'OW1', 'OW2', 'OY', 'OY0',
+  'OY1', 'OY2', 'P', 'R', 'S', 'SH', 'T', 'TH', 'UH', 'UH0', 'UH1', 'UH2', 'UW',
+  'UW0', 'UW1', 'UW2', 'V', 'W', 'Y', 'Z', 'ZH'
+]
+
+_valid_symbol_set = set(valid_symbols)
+
+
+class CMUDict:
+  '''Thin wrapper around CMUDict data. http://www.speech.cs.cmu.edu/cgi-bin/cmudict'''
+  def __init__(self, file_or_path, keep_ambiguous=True):
+    if isinstance(file_or_path, str):
+      with open(file_or_path, encoding='latin-1') as f:
+        entries = _parse_cmudict(f)
+    else:
+      entries = _parse_cmudict(file_or_path)
+    if not keep_ambiguous:
+      entries = {word: pron for word, pron in entries.items() if len(pron) == 1}
+    self._entries = entries
+
+
+  def __len__(self):
+    return len(self._entries)
+
+
+  def lookup(self, word):
+    '''Returns list of ARPAbet pronunciations of the given word.'''
+    return self._entries.get(word.upper())
+
+
+
+_alt_re = re.compile(r'\([0-9]+\)')
+
+
+def _parse_cmudict(file):
+  cmudict = {}
+  for line in file:
+    if len(line) and (line[0] >= 'A' and line[0] <= 'Z' or line[0] == "'"):
+      parts = line.split('  ')
+      word = re.sub(_alt_re, '', parts[0])
+      pronunciation = _get_pronunciation(parts[1])
+      if pronunciation:
+        if word in cmudict:
+          cmudict[word].append(pronunciation)
+        else:
+          cmudict[word] = [pronunciation]
+  return cmudict
+
+
+def _get_pronunciation(s):
+  parts = s.strip().split(' ')
+  for part in parts:
+    if part not in _valid_symbol_set:
+      return None
+  return ' '.join(parts)

text/numbers.py

@@ -0,0 +1,71 @@
+""" from https://github.com/keithito/tacotron """
+
+import inflect
+import re
+
+
+_inflect = inflect.engine()
+_comma_number_re = re.compile(r'([0-9][0-9\,]+[0-9])')
+_decimal_number_re = re.compile(r'([0-9]+\.[0-9]+)')
+_pounds_re = re.compile(r'£([0-9\,]*[0-9]+)')
+_dollars_re = re.compile(r'\$([0-9\.\,]*[0-9]+)')
+_ordinal_re = re.compile(r'[0-9]+(st|nd|rd|th)')
+_number_re = re.compile(r'[0-9]+')
+
+
+def _remove_commas(m):
+  return m.group(1).replace(',', '')
+
+
+def _expand_decimal_point(m):
+  return m.group(1).replace('.', ' point ')
+
+
+def _expand_dollars(m):
+  match = m.group(1)
+  parts = match.split('.')
+  if len(parts) > 2:
+    return match + ' dollars'  # Unexpected format
+  dollars = int(parts[0]) if parts[0] else 0
+  cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
+  if dollars and cents:
+    dollar_unit = 'dollar' if dollars == 1 else 'dollars'
+    cent_unit = 'cent' if cents == 1 else 'cents'
+    return '%s %s, %s %s' % (dollars, dollar_unit, cents, cent_unit)
+  elif dollars:
+    dollar_unit = 'dollar' if dollars == 1 else 'dollars'
+    return '%s %s' % (dollars, dollar_unit)
+  elif cents:
+    cent_unit = 'cent' if cents == 1 else 'cents'
+    return '%s %s' % (cents, cent_unit)
+  else:
+    return 'zero dollars'
+
+
+def _expand_ordinal(m):
+  return _inflect.number_to_words(m.group(0))
+
+
+def _expand_number(m):
+  num = int(m.group(0))
+  if num > 1000 and num < 3000:
+    if num == 2000:
+      return 'two thousand'
+    elif num > 2000 and num < 2010:
+      return 'two thousand ' + _inflect.number_to_words(num % 100)
+    elif num % 100 == 0:
+      return _inflect.number_to_words(num // 100) + ' hundred'
+    else:
+      return _inflect.number_to_words(num, andword='', zero='oh', group=2).replace(', ', ' ')
+  else:
+    return _inflect.number_to_words(num, andword='')
+
+
+def normalize_numbers(text):
+  text = re.sub(_comma_number_re, _remove_commas, text)
+  text = re.sub(_pounds_re, r'\1 pounds', text)
+  text = re.sub(_dollars_re, _expand_dollars, text)
+  text = re.sub(_decimal_number_re, _expand_decimal_point, text)
+  text = re.sub(_ordinal_re, _expand_ordinal, text)
+  text = re.sub(_number_re, _expand_number, text)
+  return text

text/symbols.py

@@ -0,0 +1,18 @@
+""" from https://github.com/keithito/tacotron """
+
+'''
+Defines the set of symbols used in text input to the model.
+
+The default is a set of ASCII characters that works well for English or text that has been run through Unidecode. For other data, you can modify _characters. See TRAINING_DATA.md for details. '''
+from text import cmudict
+
+_pad        = '_'
+_punctuation = '!\'(),.:;? '
+_special = '-'
+_letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
+
+# Prepend "@" to ARPAbet symbols to ensure uniqueness (some are the same as uppercase letters):
+_arpabet = ['@' + s for s in cmudict.valid_symbols]
+
+# Export all symbols:
+symbols = [_pad] + list(_special) + list(_punctuation) + list(_letters) + _arpabet