Release Inflect-Nano-v1
This commit is contained in:
Owen Song
system
@@ -0,0 +1,19 @@
|
||||
from .symbols import *
|
||||
|
||||
|
||||
_symbol_to_id = {s: i for i, s in enumerate(symbols)}
|
||||
|
||||
|
||||
def phonemes_to_ids(cleaned_text, tones, language, symbol_to_id=None):
|
||||
"""Converts a list of phoneme symbols to a sequence of integer IDs."""
|
||||
symbol_to_id_map = symbol_to_id if symbol_to_id else _symbol_to_id
|
||||
unk_id = symbol_to_id_map.get("UNK")
|
||||
if unk_id is None:
|
||||
phones = [symbol_to_id_map[symbol] for symbol in cleaned_text]
|
||||
else:
|
||||
phones = [symbol_to_id_map.get(symbol, unk_id) for symbol in cleaned_text]
|
||||
tone_start = language_tone_start_map[language]
|
||||
tones = [i + tone_start for i in tones]
|
||||
lang_id = language_id_map[language]
|
||||
lang_ids = [lang_id for _ in phones]
|
||||
return phones, tones, lang_ids
|
||||
+129530
File diff suppressed because it is too large
Load Diff
Binary file not shown.
@@ -0,0 +1,173 @@
|
||||
import pickle
|
||||
import os
|
||||
import re
|
||||
from g2p_en import G2p
|
||||
|
||||
from . import symbols
|
||||
|
||||
from .english_utils.abbreviations import expand_abbreviations
|
||||
from .english_utils.time_norm import expand_time_english
|
||||
from .english_utils.number_norm import normalize_numbers
|
||||
|
||||
|
||||
def distribute_phone(n_phone, n_word):
|
||||
phones_per_word = [0] * n_word
|
||||
for task in range(n_phone):
|
||||
min_tasks = min(phones_per_word)
|
||||
min_indices = [
|
||||
i for i, x in enumerate(phones_per_word) if x == min_tasks
|
||||
]
|
||||
chosen_index = min_indices[len(min_indices) // 2]
|
||||
phones_per_word[chosen_index] += 1
|
||||
return phones_per_word
|
||||
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
current_file_path = os.path.dirname(__file__)
|
||||
CMU_DICT_PATH = os.path.join(current_file_path, "cmudict.rep")
|
||||
CACHE_PATH = os.path.join(current_file_path, "cmudict_cache.pickle")
|
||||
_g2p = G2p()
|
||||
|
||||
arpa = {
|
||||
"AH0", "S", "AH1", "EY2", "AE2", "EH0", "OW2", "UH0", "NG", "B",
|
||||
"G", "AY0", "M", "AA0", "F", "AO0", "ER2", "UH1", "IY1", "AH2",
|
||||
"DH", "IY0", "EY1", "IH0", "K", "N", "W", "IY2", "T", "AA1",
|
||||
"ER1", "EH2", "OY0", "UH2", "UW1", "Z", "AW2", "AW1", "V", "UW2",
|
||||
"AA2", "ER", "AW0", "UW0", "R", "OW1", "EH1", "ZH", "AE0", "IH2",
|
||||
"IH", "Y", "JH", "P", "AY1", "EY0", "OY2", "TH", "HH", "D",
|
||||
"ER0", "CH", "AO1", "AE1", "AO2", "OY1", "AY2", "IH1", "OW0", "L", "SH",
|
||||
}
|
||||
|
||||
|
||||
def map_phoneme(ph):
|
||||
rep_map = {
|
||||
"：": ",", "；": ",", "，": ",", "。": ".", "！": "!",
|
||||
"？": "?", "\n": ".", "·": ",", "、": ",", "...": "…", "v": "V",
|
||||
}
|
||||
if ph in rep_map.keys():
|
||||
ph = rep_map[ph]
|
||||
if ph in symbols:
|
||||
return ph
|
||||
if ph not in symbols:
|
||||
ph = "UNK"
|
||||
return ph
|
||||
|
||||
|
||||
def read_dict():
|
||||
g2p_dict = {}
|
||||
start_line = 49
|
||||
with open(CMU_DICT_PATH) as f:
|
||||
line = f.readline()
|
||||
line_index = 1
|
||||
while line:
|
||||
if line_index >= start_line:
|
||||
line = line.strip()
|
||||
word_split = line.split(" ")
|
||||
word = word_split[0]
|
||||
|
||||
syllable_split = word_split[1].split(" - ")
|
||||
g2p_dict[word] = []
|
||||
for syllable in syllable_split:
|
||||
phone_split = syllable.split(" ")
|
||||
g2p_dict[word].append(phone_split)
|
||||
|
||||
line_index = line_index + 1
|
||||
line = f.readline()
|
||||
|
||||
return g2p_dict
|
||||
|
||||
|
||||
def cache_dict(g2p_dict, file_path):
|
||||
with open(file_path, "wb") as pickle_file:
|
||||
pickle.dump(g2p_dict, pickle_file)
|
||||
|
||||
|
||||
def get_dict():
|
||||
if os.path.exists(CACHE_PATH):
|
||||
with open(CACHE_PATH, "rb") as pickle_file:
|
||||
g2p_dict = pickle.load(pickle_file)
|
||||
else:
|
||||
g2p_dict = read_dict()
|
||||
cache_dict(g2p_dict, CACHE_PATH)
|
||||
|
||||
return g2p_dict
|
||||
|
||||
|
||||
eng_dict = get_dict()
|
||||
|
||||
|
||||
def parse_phoneme(phn):
|
||||
tone = 0
|
||||
if re.search(r"\d$", phn):
|
||||
tone = int(phn[-1]) + 1
|
||||
phn = phn[:-1]
|
||||
return phn.lower(), tone
|
||||
|
||||
|
||||
def parse_syllables(syllables):
|
||||
tones = []
|
||||
phonemes = []
|
||||
for phn_list in syllables:
|
||||
for i in range(len(phn_list)):
|
||||
phn = phn_list[i]
|
||||
phn, tone = parse_phoneme(phn)
|
||||
phonemes.append(phn)
|
||||
tones.append(tone)
|
||||
return phonemes, tones
|
||||
|
||||
|
||||
def normalize_text(text):
|
||||
text = text.lower()
|
||||
text = expand_time_english(text)
|
||||
text = normalize_numbers(text)
|
||||
text = expand_abbreviations(text)
|
||||
return text
|
||||
|
||||
|
||||
model_id = 'bert-base-uncased'
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
|
||||
|
||||
def grapheme_to_phoneme(text, pad_start_end=True, tokenized=None):
|
||||
if tokenized is None:
|
||||
tokenized = tokenizer.tokenize(text)
|
||||
ph_groups = []
|
||||
for t in tokenized:
|
||||
if not t.startswith("#"):
|
||||
ph_groups.append([t])
|
||||
else:
|
||||
ph_groups[-1].append(t.replace("#", ""))
|
||||
|
||||
phones = []
|
||||
tones = []
|
||||
word2ph = []
|
||||
for group in ph_groups:
|
||||
w = "".join(group)
|
||||
phone_len = 0
|
||||
word_len = len(group)
|
||||
if w.upper() in eng_dict:
|
||||
phns, tns = parse_syllables(eng_dict[w.upper()])
|
||||
phones += phns
|
||||
tones += tns
|
||||
phone_len += len(phns)
|
||||
else:
|
||||
phone_list = list(filter(lambda p: p != " ", _g2p(w)))
|
||||
for ph in phone_list:
|
||||
if ph in arpa:
|
||||
ph, tn = parse_phoneme(ph)
|
||||
phones.append(ph)
|
||||
tones.append(tn)
|
||||
else:
|
||||
phones.append(ph)
|
||||
tones.append(0)
|
||||
phone_len += 1
|
||||
aaa = distribute_phone(phone_len, word_len)
|
||||
word2ph += aaa
|
||||
phones = [map_phoneme(i) for i in phones]
|
||||
|
||||
if pad_start_end:
|
||||
phones = ["_"] + phones + ["_"]
|
||||
tones = [0] + tones + [0]
|
||||
word2ph = [1] + word2ph + [1]
|
||||
return phones, tones, word2ph
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,35 @@
|
||||
import re
|
||||
|
||||
# List of (regular expression, replacement) pairs for abbreviations in english:
|
||||
abbreviations_en = [
|
||||
(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, lang="en"):
|
||||
if lang == "en":
|
||||
_abbreviations = abbreviations_en
|
||||
else:
|
||||
raise NotImplementedError()
|
||||
for regex, replacement in _abbreviations:
|
||||
text = re.sub(regex, replacement, text)
|
||||
return text
|
||||
@@ -0,0 +1,97 @@
|
||||
""" from https://github.com/keithito/tacotron """
|
||||
|
||||
import re
|
||||
from typing import Dict
|
||||
|
||||
import inflect
|
||||
|
||||
_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]+)")
|
||||
_currency_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_currency(value: str, inflection: Dict[float, str]) -> str:
|
||||
parts = value.replace(",", "").split(".")
|
||||
if len(parts) > 2:
|
||||
return f"{value} {inflection[2]}" # Unexpected format
|
||||
text = []
|
||||
integer = int(parts[0]) if parts[0] else 0
|
||||
if integer > 0:
|
||||
integer_unit = inflection.get(integer, inflection[2])
|
||||
text.append(f"{integer} {integer_unit}")
|
||||
fraction = int(parts[1]) if len(parts) > 1 and parts[1] else 0
|
||||
if fraction > 0:
|
||||
fraction_unit = inflection.get(fraction / 100, inflection[0.02])
|
||||
text.append(f"{fraction} {fraction_unit}")
|
||||
if len(text) == 0:
|
||||
return f"zero {inflection[2]}"
|
||||
return " ".join(text)
|
||||
|
||||
|
||||
def _expand_currency(m: "re.Match") -> str:
|
||||
currencies = {
|
||||
"$": {
|
||||
0.01: "cent",
|
||||
0.02: "cents",
|
||||
1: "dollar",
|
||||
2: "dollars",
|
||||
},
|
||||
"€": {
|
||||
0.01: "cent",
|
||||
0.02: "cents",
|
||||
1: "euro",
|
||||
2: "euros",
|
||||
},
|
||||
"£": {
|
||||
0.01: "penny",
|
||||
0.02: "pence",
|
||||
1: "pound sterling",
|
||||
2: "pounds sterling",
|
||||
},
|
||||
"¥": {
|
||||
# TODO rin
|
||||
0.02: "sen",
|
||||
2: "yen",
|
||||
},
|
||||
}
|
||||
unit = m.group(1)
|
||||
currency = currencies[unit]
|
||||
value = m.group(2)
|
||||
return __expand_currency(value, currency)
|
||||
|
||||
|
||||
def _expand_ordinal(m):
|
||||
return _inflect.number_to_words(m.group(0))
|
||||
|
||||
|
||||
def _expand_number(m):
|
||||
num = int(m.group(0))
|
||||
if 1000 < num < 3000:
|
||||
if num == 2000:
|
||||
return "two thousand"
|
||||
if 2000 < num < 2010:
|
||||
return "two thousand " + _inflect.number_to_words(num % 100)
|
||||
if num % 100 == 0:
|
||||
return _inflect.number_to_words(num // 100) + " hundred"
|
||||
return _inflect.number_to_words(num, andword="", zero="oh", group=2).replace(", ", " ")
|
||||
return _inflect.number_to_words(num, andword="")
|
||||
|
||||
|
||||
def normalize_numbers(text):
|
||||
text = re.sub(_comma_number_re, _remove_commas, text)
|
||||
text = re.sub(_currency_re, _expand_currency, 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
|
||||
@@ -0,0 +1,47 @@
|
||||
import re
|
||||
|
||||
import inflect
|
||||
|
||||
_inflect = inflect.engine()
|
||||
|
||||
_time_re = re.compile(
|
||||
r"""\b
|
||||
((0?[0-9])|(1[0-1])|(1[2-9])|(2[0-3])) # hours
|
||||
:
|
||||
([0-5][0-9]) # minutes
|
||||
\s*(a\\.m\\.|am|pm|p\\.m\\.|a\\.m|p\\.m)? # am/pm
|
||||
\b""",
|
||||
re.IGNORECASE | re.X,
|
||||
)
|
||||
|
||||
|
||||
def _expand_num(n: int) -> str:
|
||||
return _inflect.number_to_words(n)
|
||||
|
||||
|
||||
def _expand_time_english(match: "re.Match") -> str:
|
||||
hour = int(match.group(1))
|
||||
past_noon = hour >= 12
|
||||
time = []
|
||||
if hour > 12:
|
||||
hour -= 12
|
||||
elif hour == 0:
|
||||
hour = 12
|
||||
past_noon = True
|
||||
time.append(_expand_num(hour))
|
||||
|
||||
minute = int(match.group(6))
|
||||
if minute > 0:
|
||||
if minute < 10:
|
||||
time.append("oh")
|
||||
time.append(_expand_num(minute))
|
||||
am_pm = match.group(7)
|
||||
if am_pm is None:
|
||||
time.append("p m" if past_noon else "a m")
|
||||
else:
|
||||
time.extend(list(am_pm.replace(".", "")))
|
||||
return " ".join(time)
|
||||
|
||||
|
||||
def expand_time_english(text: str) -> str:
|
||||
return re.sub(_time_re, _expand_time_english, text)
|
||||
@@ -0,0 +1,293 @@
|
||||
# punctuation = ["!", "?", "…", ",", ".", "'", "-"]
|
||||
punctuation = ["!", "?", "…", ",", ".", "'", "-", "¿", "¡"]
|
||||
pu_symbols = punctuation + ["SP", "UNK"]
|
||||
pad = "_"
|
||||
|
||||
# chinese
|
||||
zh_symbols = [
|
||||
"E",
|
||||
"En",
|
||||
"a",
|
||||
"ai",
|
||||
"an",
|
||||
"ang",
|
||||
"ao",
|
||||
"b",
|
||||
"c",
|
||||
"ch",
|
||||
"d",
|
||||
"e",
|
||||
"ei",
|
||||
"en",
|
||||
"eng",
|
||||
"er",
|
||||
"f",
|
||||
"g",
|
||||
"h",
|
||||
"i",
|
||||
"i0",
|
||||
"ia",
|
||||
"ian",
|
||||
"iang",
|
||||
"iao",
|
||||
"ie",
|
||||
"in",
|
||||
"ing",
|
||||
"iong",
|
||||
"ir",
|
||||
"iu",
|
||||
"j",
|
||||
"k",
|
||||
"l",
|
||||
"m",
|
||||
"n",
|
||||
"o",
|
||||
"ong",
|
||||
"ou",
|
||||
"p",
|
||||
"q",
|
||||
"r",
|
||||
"s",
|
||||
"sh",
|
||||
"t",
|
||||
"u",
|
||||
"ua",
|
||||
"uai",
|
||||
"uan",
|
||||
"uang",
|
||||
"ui",
|
||||
"un",
|
||||
"uo",
|
||||
"v",
|
||||
"van",
|
||||
"ve",
|
||||
"vn",
|
||||
"w",
|
||||
"x",
|
||||
"y",
|
||||
"z",
|
||||
"zh",
|
||||
"AA",
|
||||
"EE",
|
||||
"OO",
|
||||
]
|
||||
num_zh_tones = 6
|
||||
|
||||
# japanese
|
||||
ja_symbols = [
|
||||
"N",
|
||||
"a",
|
||||
"a:",
|
||||
"b",
|
||||
"by",
|
||||
"ch",
|
||||
"d",
|
||||
"dy",
|
||||
"e",
|
||||
"e:",
|
||||
"f",
|
||||
"g",
|
||||
"gy",
|
||||
"h",
|
||||
"hy",
|
||||
"i",
|
||||
"i:",
|
||||
"j",
|
||||
"k",
|
||||
"ky",
|
||||
"m",
|
||||
"my",
|
||||
"n",
|
||||
"ny",
|
||||
"o",
|
||||
"o:",
|
||||
"p",
|
||||
"py",
|
||||
"q",
|
||||
"r",
|
||||
"ry",
|
||||
"s",
|
||||
"sh",
|
||||
"t",
|
||||
"ts",
|
||||
"ty",
|
||||
"u",
|
||||
"u:",
|
||||
"w",
|
||||
"y",
|
||||
"z",
|
||||
"zy",
|
||||
]
|
||||
num_ja_tones = 1
|
||||
|
||||
# English
|
||||
en_symbols = [
|
||||
"aa",
|
||||
"ae",
|
||||
"ah",
|
||||
"ao",
|
||||
"aw",
|
||||
"ay",
|
||||
"b",
|
||||
"ch",
|
||||
"d",
|
||||
"dh",
|
||||
"eh",
|
||||
"er",
|
||||
"ey",
|
||||
"f",
|
||||
"g",
|
||||
"hh",
|
||||
"ih",
|
||||
"iy",
|
||||
"jh",
|
||||
"k",
|
||||
"l",
|
||||
"m",
|
||||
"n",
|
||||
"ng",
|
||||
"ow",
|
||||
"oy",
|
||||
"p",
|
||||
"r",
|
||||
"s",
|
||||
"sh",
|
||||
"t",
|
||||
"th",
|
||||
"uh",
|
||||
"uw",
|
||||
"V",
|
||||
"w",
|
||||
"y",
|
||||
"z",
|
||||
"zh",
|
||||
]
|
||||
num_en_tones = 4
|
||||
|
||||
# Korean
|
||||
kr_symbols = ['ᄌ', 'ᅥ', 'ᆫ', 'ᅦ', 'ᄋ', 'ᅵ', 'ᄅ', 'ᅴ', 'ᄀ', 'ᅡ', 'ᄎ', 'ᅪ', 'ᄑ', 'ᅩ', 'ᄐ', 'ᄃ', 'ᅢ', 'ᅮ', 'ᆼ', 'ᅳ', 'ᄒ', 'ᄆ', 'ᆯ', 'ᆷ', 'ᄂ', 'ᄇ', 'ᄉ', 'ᆮ', 'ᄁ', 'ᅬ', 'ᅣ', 'ᄄ', 'ᆨ', 'ᄍ', 'ᅧ', 'ᄏ', 'ᆸ', 'ᅭ', '(', 'ᄊ', ')', 'ᅲ', 'ᅨ', 'ᄈ', 'ᅱ', 'ᅯ', 'ᅫ', 'ᅰ', 'ᅤ', '~', '\\', '[', ']', '/', '^', ':', 'ㄸ', '*']
|
||||
num_kr_tones = 1
|
||||
|
||||
# Spanish
|
||||
es_symbols = [
|
||||
"N",
|
||||
"Q",
|
||||
"a",
|
||||
"b",
|
||||
"d",
|
||||
"e",
|
||||
"f",
|
||||
"g",
|
||||
"h",
|
||||
"i",
|
||||
"j",
|
||||
"k",
|
||||
"l",
|
||||
"m",
|
||||
"n",
|
||||
"o",
|
||||
"p",
|
||||
"s",
|
||||
"t",
|
||||
"u",
|
||||
"v",
|
||||
"w",
|
||||
"x",
|
||||
"y",
|
||||
"z",
|
||||
"ɑ",
|
||||
"æ",
|
||||
"ʃ",
|
||||
"ʑ",
|
||||
"ç",
|
||||
"ɯ",
|
||||
"ɪ",
|
||||
"ɔ",
|
||||
"ɛ",
|
||||
"ɹ",
|
||||
"ð",
|
||||
"ə",
|
||||
"ɫ",
|
||||
"ɥ",
|
||||
"ɸ",
|
||||
"ʊ",
|
||||
"ɾ",
|
||||
"ʒ",
|
||||
"θ",
|
||||
"β",
|
||||
"ŋ",
|
||||
"ɦ",
|
||||
"ɡ",
|
||||
"r",
|
||||
"ɲ",
|
||||
"ʝ",
|
||||
"ɣ",
|
||||
"ʎ",
|
||||
"ˈ",
|
||||
"ˌ",
|
||||
"ː"
|
||||
]
|
||||
num_es_tones = 1
|
||||
|
||||
# French
|
||||
fr_symbols = [
|
||||
"\u0303",
|
||||
"œ",
|
||||
"ø",
|
||||
"ʁ",
|
||||
"ɒ",
|
||||
"ʌ",
|
||||
"ɜ",
|
||||
"ɐ"
|
||||
]
|
||||
num_fr_tones = 1
|
||||
|
||||
# German
|
||||
de_symbols = [
|
||||
"ʏ",
|
||||
"̩"
|
||||
]
|
||||
num_de_tones = 1
|
||||
|
||||
# Russian
|
||||
ru_symbols = [
|
||||
"ɭ",
|
||||
"ʲ",
|
||||
"ɕ",
|
||||
"\"",
|
||||
"ɵ",
|
||||
"^",
|
||||
"ɬ"
|
||||
]
|
||||
num_ru_tones = 1
|
||||
|
||||
# combine all symbols
|
||||
normal_symbols = sorted(set(zh_symbols + ja_symbols + en_symbols + kr_symbols + es_symbols + fr_symbols + de_symbols + ru_symbols))
|
||||
symbols = [pad] + normal_symbols + pu_symbols
|
||||
sil_phonemes_ids = [symbols.index(i) for i in pu_symbols]
|
||||
|
||||
# combine all tones
|
||||
num_tones = num_zh_tones + num_ja_tones + num_en_tones + num_kr_tones + num_es_tones + num_fr_tones + num_de_tones + num_ru_tones
|
||||
|
||||
# language maps
|
||||
language_id_map = {"ZH": 0, "JP": 1, "EN": 2, "ZH_MIX_EN": 3, 'KR': 4, 'ES': 5, 'SP': 5, 'FR': 6, 'DE': 7, 'RU': 8, 'VI': 9}
|
||||
num_languages = 10
|
||||
|
||||
language_tone_start_map = {
|
||||
"ZH": 0,
|
||||
"ZH_MIX_EN": 0,
|
||||
"JP": num_zh_tones,
|
||||
"EN": num_zh_tones + num_ja_tones,
|
||||
'KR': num_zh_tones + num_ja_tones + num_en_tones,
|
||||
"ES": num_zh_tones + num_ja_tones + num_en_tones + num_kr_tones,
|
||||
"SP": num_zh_tones + num_ja_tones + num_en_tones + num_kr_tones,
|
||||
"FR": num_zh_tones + num_ja_tones + num_en_tones + num_kr_tones + num_es_tones,
|
||||
"DE": num_zh_tones + num_ja_tones + num_en_tones + num_kr_tones + num_es_tones + num_fr_tones,
|
||||
"RU": num_zh_tones + num_ja_tones + num_en_tones + num_kr_tones + num_es_tones + num_fr_tones + num_de_tones,
|
||||
"VI": num_zh_tones + num_ja_tones + num_en_tones + num_kr_tones + num_es_tones + num_fr_tones + num_de_tones + num_ru_tones,
|
||||
}
|
||||
|
||||
if __name__ == "__main__":
|
||||
a = set(zh_symbols)
|
||||
b = set(en_symbols)
|
||||
print(sorted(a & b))
|
||||
Reference in New Issue
Block a user