Spaces:
Build error
Build error
File size: 2,497 Bytes
b93970c |
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 |
import re
from data_gen.tts.data_gen_utils import PUNCS
from g2p_en import G2p
import unicodedata
from g2p_en.expand import normalize_numbers
from nltk import pos_tag
from nltk.tokenize import TweetTokenizer
from data_gen.tts.txt_processors.base_text_processor import BaseTxtProcessor
class EnG2p(G2p):
word_tokenize = TweetTokenizer().tokenize
def __call__(self, text):
# preprocessing
words = EnG2p.word_tokenize(text)
tokens = pos_tag(words) # tuples of (word, tag)
# steps
prons = []
for word, pos in tokens:
if re.search("[a-z]", word) is None:
pron = [word]
elif word in self.homograph2features: # Check homograph
pron1, pron2, pos1 = self.homograph2features[word]
if pos.startswith(pos1):
pron = pron1
else:
pron = pron2
elif word in self.cmu: # lookup CMU dict
pron = self.cmu[word][0]
else: # predict for oov
pron = self.predict(word)
prons.extend(pron)
prons.extend([" "])
return prons[:-1]
class TxtProcessor(BaseTxtProcessor):
g2p = EnG2p()
@staticmethod
def preprocess_text(text):
text = normalize_numbers(text)
text = ''.join(char for char in unicodedata.normalize('NFD', text)
if unicodedata.category(char) != 'Mn') # Strip accents
text = text.lower()
text = re.sub("[\'\"()]+", "", text)
text = re.sub("[-]+", " ", text)
text = re.sub(f"[^ a-z{PUNCS}]", "", text)
text = re.sub(f" ?([{PUNCS}]) ?", r"\1", text) # !! -> !
text = re.sub(f"([{PUNCS}])+", r"\1", text) # !! -> !
text = text.replace("i.e.", "that is")
text = text.replace("i.e.", "that is")
text = text.replace("etc.", "etc")
text = re.sub(f"([{PUNCS}])", r" \1 ", text)
text = re.sub(rf"\s+", r" ", text)
return text
@classmethod
def process(cls, txt, pre_align_args):
txt = cls.preprocess_text(txt).strip()
phs = cls.g2p(txt)
phs_ = []
n_word_sep = 0
for p in phs:
if p.strip() == '':
phs_ += ['|']
n_word_sep += 1
else:
phs_ += p.split(" ")
phs = phs_
assert n_word_sep + 1 == len(txt.split(" ")), (phs, f"\"{txt}\"")
return phs, txt
|