Espeak phonemizer pipeline for spanish (and also english)

This commit is contained in:
Mathias Gatti
2022-07-14 22:14:32 -03:00
parent 2e6be74403
commit 840a97e70e
13 changed files with 491 additions and 15 deletions
@@ -0,0 +1,19 @@
_pad = '_'
_punctuation = '!\'(),.:;? ' #NB: Includes space
_special = '-'
_letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
# https://en.wikipedia.org/wiki/ARPABET
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'
]
extra_replacements = {}
@@ -0,0 +1,34 @@
# https://en.wikipedia.org/wiki/ARPABET
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', "RR", "NI"
]
extra_replacements = {
"a": "AA0",
"o": "OW0",
"β": "V",
"e": "EY0",
"ɲ": "NI",
"r": "RR",
"ɣ": "G",
"ʎ": "SH",
"x": "HH",
"ts": "TH", # jacuzzi / pizza
"oɪ": "OW0 Y", # acoitar
"eʊ": "EY0 W", # adeuda
"ʝ": "SH" # ya
}
# NB: DO NOT CHANGE THE ORDER OF SYMBOLS!
# Models are trained on and depend upon the order.
pad = '_'
punctuation = '!\'(),.:;? '
special = '-'
# Little hack, since I'm using arpabet letters are not useful anymore, I just replace it with spanish symbols that I need like ¡ and ¿
letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwx¡¿'