File size: 1,205 Bytes
83d190a |
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 |
import re
import cn2an
from style_bert_vits2.nlp.symbols import PUNCTUATIONS
__REPLACE_MAP = {
"：": ",",
"；": ",",
"，": ",",
"。": ".",
"！": "!",
"？": "?",
"\n": ".",
"·": ",",
"、": ",",
"...": "…",
"$": ".",
"“": "'",
"”": "'",
'"': "'",
"‘": "'",
"’": "'",
"（": "'",
"）": "'",
"(": "'",
")": "'",
"《": "'",
"》": "'",
"【": "'",
"】": "'",
"[": "'",
"]": "'",
"—": "-",
"～": "-",
"~": "-",
"「": "'",
"」": "'",
}
def normalize_text(text: str) -> str:
numbers = re.findall(r"\d+(?:\.?\d+)?", text)
for number in numbers:
text = text.replace(number, cn2an.an2cn(number), 1)
text = replace_punctuation(text)
return text
def replace_punctuation(text: str) -> str:
text = text.replace("嗯", "恩").replace("呣", "母")
pattern = re.compile("|".join(re.escape(p) for p in __REPLACE_MAP))
replaced_text = pattern.sub(lambda x: __REPLACE_MAP[x.group()], text)
replaced_text = re.sub(
r"[^\u4e00-\u9fa5" + "".join(PUNCTUATIONS) + r"]+", "", replaced_text
)
return replaced_text
|