XzJosh's picture
Upload 201 files
ae80214
import pickle
import os
import re
from g2p_en import G2p
from transformers import DebertaV2Tokenizer
from text import symbols
from text.symbols import punctuation
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()
LOCAL_PATH = "./bert/deberta-v3-large"
tokenizer = DebertaV2Tokenizer.from_pretrained(LOCAL_PATH)
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 post_replace_ph(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
rep_map = {
":": ",",
";": ",",
",": ",",
"。": ".",
"!": "!",
"?": "?",
"\n": ".",
".": ".",
"…": "...",
"···": "...",
"・・・": "...",
"·": ",",
"・": ",",
"、": ",",
"$": ".",
"“": "'",
"”": "'",
'"': "'",
"‘": "'",
"’": "'",
"(": "'",
")": "'",
"(": "'",
")": "'",
"《": "'",
"》": "'",
"【": "'",
"】": "'",
"[": "'",
"]": "'",
"—": "-",
"−": "-",
"~": "-",
"~": "-",
"「": "'",
"」": "'",
}
def replace_punctuation(text):
pattern = re.compile("|".join(re.escape(p) for p in rep_map.keys()))
replaced_text = pattern.sub(lambda x: rep_map[x.group()], text)
# replaced_text = re.sub(
# r"[^\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\u3005"
# + "".join(punctuation)
# + r"]+",
# "",
# replaced_text,
# )
return replaced_text
def read_dict():
g2p_dict = {}
start_line = 49
with open(CMU_DICT_PATH) as f:
line = f.readline()
line_index = 1
while line:
if line_index >= start_line:
line = line.strip()
word_split = line.split(" ")
word = word_split[0]
syllable_split = word_split[1].split(" - ")
g2p_dict[word] = []
for syllable in syllable_split:
phone_split = syllable.split(" ")
g2p_dict[word].append(phone_split)
line_index = line_index + 1
line = f.readline()
return g2p_dict
def cache_dict(g2p_dict, file_path):
with open(file_path, "wb") as pickle_file:
pickle.dump(g2p_dict, pickle_file)
def get_dict():
if os.path.exists(CACHE_PATH):
with open(CACHE_PATH, "rb") as pickle_file:
g2p_dict = pickle.load(pickle_file)
else:
g2p_dict = read_dict()
cache_dict(g2p_dict, CACHE_PATH)
return g2p_dict
eng_dict = get_dict()
def refine_ph(phn):
tone = 0
if re.search(r"\d$", phn):
tone = int(phn[-1]) + 1
phn = phn[:-1]
else:
tone = 3
return phn.lower(), tone
def refine_syllables(syllables):
tones = []
phonemes = []
for phn_list in syllables:
for i in range(len(phn_list)):
phn = phn_list[i]
phn, tone = refine_ph(phn)
phonemes.append(phn)
tones.append(tone)
return phonemes, tones
import re
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]+)")
_pounds_re = re.compile(r"£([0-9\,]*[0-9]+)")
_dollars_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]+")
# List of (regular expression, replacement) pairs for abbreviations:
_abbreviations = [
(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"),
]
]
# List of (ipa, lazy ipa) pairs:
_lazy_ipa = [
(re.compile("%s" % x[0]), x[1])
for x in [
("r", "ɹ"),
("æ", "e"),
("ɑ", "a"),
("ɔ", "o"),
("ð", "z"),
("θ", "s"),
("ɛ", "e"),
("ɪ", "i"),
("ʊ", "u"),
("ʒ", "ʥ"),
("ʤ", "ʥ"),
("ˈ", "↓"),
]
]
# List of (ipa, lazy ipa2) pairs:
_lazy_ipa2 = [
(re.compile("%s" % x[0]), x[1])
for x in [
("r", "ɹ"),
("ð", "z"),
("θ", "s"),
("ʒ", "ʑ"),
("ʤ", "dʑ"),
("ˈ", "↓"),
]
]
# List of (ipa, ipa2) pairs
_ipa_to_ipa2 = [
(re.compile("%s" % x[0]), x[1]) for x in [("r", "ɹ"), ("ʤ", "dʒ"), ("ʧ", "tʃ")]
]
def _expand_dollars(m):
match = m.group(1)
parts = match.split(".")
if len(parts) > 2:
return match + " dollars" # Unexpected format
dollars = int(parts[0]) if parts[0] else 0
cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
if dollars and cents:
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:
dollar_unit = "dollar" if dollars == 1 else "dollars"
return "%s %s" % (dollars, dollar_unit)
elif cents:
cent_unit = "cent" if cents == 1 else "cents"
return "%s %s" % (cents, cent_unit)
else:
return "zero dollars"
def _remove_commas(m):
return m.group(1).replace(",", "")
def _expand_ordinal(m):
return _inflect.number_to_words(m.group(0))
def _expand_number(m):
num = int(m.group(0))
if num > 1000 and num < 3000:
if num == 2000:
return "two thousand"
elif num > 2000 and num < 2010:
return "two thousand " + _inflect.number_to_words(num % 100)
elif num % 100 == 0:
return _inflect.number_to_words(num // 100) + " hundred"
else:
return _inflect.number_to_words(
num, andword="", zero="oh", group=2
).replace(", ", " ")
else:
return _inflect.number_to_words(num, andword="")
def _expand_decimal_point(m):
return m.group(1).replace(".", " point ")
def normalize_numbers(text):
text = re.sub(_comma_number_re, _remove_commas, text)
text = re.sub(_pounds_re, r"\1 pounds", text)
text = re.sub(_dollars_re, _expand_dollars, 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
def text_normalize(text):
text = normalize_numbers(text)
text = replace_punctuation(text)
text = re.sub(r"([,;.\?\!])([\w])", r"\1 \2", text)
return text
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_index = phones_per_word.index(min_tasks)
phones_per_word[min_index] += 1
return phones_per_word
def sep_text(text):
words = re.split(r"([,;.\?\!\s+])", text)
words = [word for word in words if word.strip() != ""]
return words
def text_to_words(text):
tokens = tokenizer.tokenize(text)
words = []
for idx, t in enumerate(tokens):
if t.startswith("▁"):
words.append([t[1:]])
else:
if t in punctuation:
if idx == len(tokens) - 1:
words.append([f"{t}"])
else:
if (
not tokens[idx + 1].startswith("▁")
and tokens[idx + 1] not in punctuation
):
if idx == 0:
words.append([])
words[-1].append(f"{t}")
else:
words.append([f"{t}"])
else:
if idx == 0:
words.append([])
words[-1].append(f"{t}")
return words
def g2p(text):
phones = []
tones = []
phone_len = []
# words = sep_text(text)
# tokens = [tokenizer.tokenize(i) for i in words]
words = text_to_words(text)
for word in words:
temp_phones, temp_tones = [], []
if len(word) > 1:
if "'" in word:
word = ["".join(word)]
for w in word:
if w in punctuation:
temp_phones.append(w)
temp_tones.append(0)
continue
if w.upper() in eng_dict:
phns, tns = refine_syllables(eng_dict[w.upper()])
temp_phones += [post_replace_ph(i) for i in phns]
temp_tones += tns
# w2ph.append(len(phns))
else:
phone_list = list(filter(lambda p: p != " ", _g2p(w)))
phns = []
tns = []
for ph in phone_list:
if ph in arpa:
ph, tn = refine_ph(ph)
phns.append(ph)
tns.append(tn)
else:
phns.append(ph)
tns.append(0)
temp_phones += [post_replace_ph(i) for i in phns]
temp_tones += tns
phones += temp_phones
tones += temp_tones
phone_len.append(len(temp_phones))
# phones = [post_replace_ph(i) for i in phones]
word2ph = []
for token, pl in zip(words, phone_len):
word_len = len(token)
aaa = distribute_phone(pl, word_len)
word2ph += aaa
phones = ["_"] + phones + ["_"]
tones = [0] + tones + [0]
word2ph = [1] + word2ph + [1]
assert len(phones) == len(tones), text
assert len(phones) == sum(word2ph), text
return phones, tones, word2ph
def get_bert_feature(text, word2ph):
from text import english_bert_mock
return english_bert_mock.get_bert_feature(text, word2ph)
if __name__ == "__main__":
# print(get_dict())
# print(eng_word_to_phoneme("hello"))
print(g2p("In this paper, we propose 1 DSPGAN, a GAN-based universal vocoder."))
# all_phones = set()
# for k, syllables in eng_dict.items():
# for group in syllables:
# for ph in group:
# all_phones.add(ph)
# print(all_phones)