wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-09 11:16:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix Pylint issues

Browse Source
This commit is contained in:
Reuben Morais
2019-07-19 09:08:51 +02:00
parent 509292d56a
commit 11e7895329
35 changed files with 270 additions and 316 deletions
Download Patch File Download Diff File Expand all files Collapse all files
utils/text/__init__.py
+25 -25
View File
@@ -7,17 +7,17 @@ from utils.text import cleaners
from utils.text.symbols import symbols, phonemes, _phoneme_punctuations
# Mappings from symbol to numeric ID and vice versa:
_symbol_to_id = {s: i for i, s in enumerate(symbols)}
_id_to_symbol = {i: s for i, s in enumerate(symbols)}
_SYMBOL_TO_ID = {s: i for i, s in enumerate(symbols)}
_ID_TO_SYMBOL = {i: s for i, s in enumerate(symbols)}
_phonemes_to_id = {s: i for i, s in enumerate(phonemes)}
_id_to_phonemes = {i: s for i, s in enumerate(phonemes)}
_PHONEMES_TO_ID = {s: i for i, s in enumerate(phonemes)}
_ID_TO_PHONEMES = {i: s for i, s in enumerate(phonemes)}
# Regular expression matching text enclosed in curly braces:
_curly_re = re.compile(r'(.*?)\{(.+?)\}(.*)')
_CURLY_RE = re.compile(r'(.*?)\{(.+?)\}(.*)')
# Regular expression matchinf punctuations, ignoring empty space
pat = r'['+_phoneme_punctuations+']+'
PHONEME_PUNCTUATION_PATTERN = r'['+_phoneme_punctuations+']+'
def text2phone(text, language):
@@ -26,11 +26,11 @@ def text2phone(text, language):
'''
seperator = phonemizer.separator.Separator(' |', '', '|')
#try:
punctuations = re.findall(pat, text)
punctuations = re.findall(PHONEME_PUNCTUATION_PATTERN, text)
ph = phonemize(text, separator=seperator, strip=False, njobs=1, backend='espeak', language=language)
ph = ph[:-1].strip() # skip the last empty character
# Replace \n with matching punctuations.
if len(punctuations) > 0:
if punctuations:
# if text ends with a punctuation.
if text[-1] == punctuations[-1]:
for punct in punctuations[:-1]:
@@ -47,20 +47,20 @@ def text2phone(text, language):
def phoneme_to_sequence(text, cleaner_names, language, enable_eos_bos=False):
if enable_eos_bos:
sequence = [_phonemes_to_id['^']]
sequence = [_PHONEMES_TO_ID['^']]
else:
sequence = []
text = text.replace(":", "")
clean_text = _clean_text(text, cleaner_names)
phonemes = text2phone(clean_text, language)
if phonemes is None:
to_phonemes = text2phone(clean_text, language)
if to_phonemes is None:
print("!! After phoneme conversion the result is None. -- {} ".format(clean_text))
# iterate by skipping empty strings - NOTE: might be useful to keep it to have a better intonation.
for phoneme in filter(None, phonemes.split('|')):
for phoneme in filter(None, to_phonemes.split('|')):
sequence += _phoneme_to_sequence(phoneme)
# Append EOS char
if enable_eos_bos:
sequence.append(_phonemes_to_id['~'])
sequence.append(_PHONEMES_TO_ID['~'])
return sequence
@@ -68,8 +68,8 @@ def sequence_to_phoneme(sequence):
'''Converts a sequence of IDs back to a string'''
result = ''
for symbol_id in sequence:
if symbol_id in _id_to_phonemes:
s = _id_to_phonemes[symbol_id]
if symbol_id in _ID_TO_PHONEMES:
s = _ID_TO_PHONEMES[symbol_id]
result += s
return result.replace('}{', ' ')
@@ -89,8 +89,8 @@ def text_to_sequence(text, cleaner_names):
'''
sequence = []
# Check for curly braces and treat their contents as ARPAbet:
while len(text):
m = _curly_re.match(text)
while text:
m = _CURLY_RE.match(text)
if not m:
sequence += _symbols_to_sequence(_clean_text(text, cleaner_names))
break
@@ -105,8 +105,8 @@ def sequence_to_text(sequence):
'''Converts a sequence of IDs back to a string'''
result = ''
for symbol_id in sequence:
if symbol_id in _id_to_symbol:
s = _id_to_symbol[symbol_id]
if symbol_id in _ID_TO_SYMBOL:
s = _ID_TO_SYMBOL[symbol_id]
# Enclose ARPAbet back in curly braces:
if len(s) > 1 and s[0] == '@':
s = '{%s}' % s[1:]
@@ -123,12 +123,12 @@ def _clean_text(text, cleaner_names):
return text
def _symbols_to_sequence(symbols):
return [_symbol_to_id[s] for s in symbols if _should_keep_symbol(s)]
def _symbols_to_sequence(syms):
return [_SYMBOL_TO_ID[s] for s in syms if _should_keep_symbol(s)]
def _phoneme_to_sequence(phonemes):
return [_phonemes_to_id[s] for s in list(phonemes) if _should_keep_phoneme(s)]
def _phoneme_to_sequence(phons):
return [_PHONEMES_TO_ID[s] for s in list(phons) if _should_keep_phoneme(s)]
def _arpabet_to_sequence(text):
@@ -136,8 +136,8 @@ def _arpabet_to_sequence(text):
def _should_keep_symbol(s):
return s in _symbol_to_id and s not in ['~', '^', '_']
return s in _SYMBOL_TO_ID and s not in ['~', '^', '_']
def _should_keep_phoneme(p):
return p in _phonemes_to_id and p not in ['~', '^', '_']
return p in _PHONEMES_TO_ID and p not in ['~', '^', '_']
utils/text/cmudict.py
+17 -17
View File
@@ -2,16 +2,16 @@
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_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'
]
class CMUDict:
@@ -37,19 +37,19 @@ class CMUDict:
'''Returns list of ARPAbet pronunciations of the given word.'''
return self._entries.get(word.upper())
def get_arpabet(self, word, cmudict, punctuation_symbols):
@staticmethod
def get_arpabet(word, cmudict, punctuation_symbols):
first_symbol, last_symbol = '', ''
if len(word) > 0 and word[0] in punctuation_symbols:
if word and word[0] in punctuation_symbols:
first_symbol = word[0]
word = word[1:]
if len(word) > 0 and word[-1] in punctuation_symbols:
if word and word[-1] in punctuation_symbols:
last_symbol = word[-1]
word = word[:-1]
arpabet = cmudict.lookup(word)
if arpabet is not None:
return first_symbol + '{%s}' % arpabet[0] + last_symbol
else:
return first_symbol + word + last_symbol
return first_symbol + word + last_symbol
_alt_re = re.compile(r'\([0-9]+\)')
@@ -58,7 +58,7 @@ _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] == "'"):
if 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])
@@ -73,6 +73,6 @@ def _parse_cmudict(file):
def _get_pronunciation(s):
parts = s.strip().split(' ')
for part in parts:
if part not in _valid_symbol_set:
if part not in VALID_SYMBOLS:
return None
return ' '.join(parts)
utils/text/number_norm.py
+6 -8
View File
@@ -66,14 +66,13 @@ def _expand_dollars(m):
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:
if dollars:
dollar_unit = 'dollar' if dollars == 1 else 'dollars'
return '%s %s' % (dollars, dollar_unit)
elif cents:
if cents:
cent_unit = 'cent' if cents == 1 else 'cents'
return '%s %s' % (cents, cent_unit)
else:
return 'zero dollars'
return 'zero dollars'
def _standard_number_to_words(n, digit_group):
@@ -99,12 +98,11 @@ def _number_to_words(n):
# Handle special cases first, then go to the standard case:
if n >= 1000000000000000000:
return str(n) # Too large, just return the digits
elif n == 0:
if n == 0:
return 'zero'
elif n % 100 == 0 and n % 1000 != 0 and n < 3000:
if n % 100 == 0 and n % 1000 != 0 and n < 3000:
return _standard_number_to_words(n // 100, 0) + ' hundred'
else:
return _standard_number_to_words(n, 0)
return _standard_number_to_words(n, 0)
def _expand_number(m):