Use clap to achieve prompt controlled generation (#223)
* 快速分类音频并把yml格式结果存在训练根目录里 (#190) * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update models.py * Update webui.py * Update infer.py * Create compress_model.py * 重新提交，更新Gradio推理UI (#193) * Update webui.py * Update webui.py * 更新 train_ms.py * 更新 models.py * 更新 models.py * 更新 models.py * 更新 train_ms.py * 更新 train_ms.py * 更新 models.py * Update preprocess_text.py * Update config.json * Update train_ms.py * Update webui.py (#206) * Add files via upload (#209) * Update train_ms.py * Update train_ms.py * Update preprocess_text.py * Update train_ms.py * fix (#211) * Update emotion_clustering.py * Add files via upload * Update emotion_clustering.py * add cluster center save * Add files via upload * Update config.py * Update default_config.yml * Update config.py * Update config.py * Update emotion_clustering.py * Update emotion_clustering.py * Update config.py * Update emotion_clustering.py * Update emotion_clustering.py * Update webui.py * Update emotion_clustering.py * Update commons.py * Update emotion_clustering.py * Update webui.py * Update webui.py * Add files via upload * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update webui.py * Update emotion_clustering.py * Update emotion_clustering.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix default_config.yml. * Update infer.py * feat: support infer 2.1 models * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: support infer 2.1 models 兼容bug修复 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update train_ms.py * Add CLAP * Fix data loader * Fix infer.py * Fix webui.py * Add prompt template * Update clap_gen.py * Fix wrong environ value * Add g for dur disc * Update clap_gen.py * Fix multilang generation * Update config.json * Prompt mode * Improve slice segments performance * Add preprocess webui * Update webui_preprocess.py * Update webui_preprocess.py * Update config.py * Update default_config.yml * Update config.py * Update clap_gen.py * Delete emo_gen.py * Delete get_emo.py * Delete emotional/wav2vec2-large-robust-12-ft-emotion-msp-dim directory * Update README.md * Update README * Split val per lang * Delete emotion_clustering.py * Update default_config.yml * Update default_config.yml * Update config.py * Update preprocess_text.py * Update webui_preprocess.py * Update defalut_config.yml * Update webui_preprocess.py * Update preprocess_text.py * Random augmentation for CLAP * Update data_utils.py * Update preprocess_text.py * Add vq for CLAP features to avoid overfitting * Random dummy inputs * Update webui.py * Update models.py * Update infer.py * Apply Code Formatter Change * Update config.json * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: YYuX-1145 <138500330+YYuX-1145@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sora <654163754@qq.com> Co-authored-by: Sihan Wang <wangsihan1995@gmail.com> Co-authored-by: Stardust-minus <Stardust-minus@users.noreply.github.com>
This commit is contained in:
Stardust·减
453
oldVersion/V210/text/english.py
Normal file
453
oldVersion/V210/text/english.py
Normal file
@@ -0,0 +1,453 @@
|
||||
import pickle
|
||||
import os
|
||||
import re
|
||||
from g2p_en import G2p
|
||||
from transformers import DebertaV2Tokenizer
|
||||
|
||||
from . import symbols
|
||||
|
||||
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]
|
||||
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 g2p(text):
|
||||
phones = []
|
||||
tones = []
|
||||
# word2ph = []
|
||||
words = sep_text(text)
|
||||
tokens = [tokenizer.tokenize(i) for i in words]
|
||||
for word in words:
|
||||
if word.upper() in eng_dict:
|
||||
phns, tns = refine_syllables(eng_dict[word.upper()])
|
||||
phones.append([post_replace_ph(i) for i in phns])
|
||||
tones.append(tns)
|
||||
# word2ph.append(len(phns))
|
||||
else:
|
||||
phone_list = list(filter(lambda p: p != " ", _g2p(word)))
|
||||
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)
|
||||
phones.append([post_replace_ph(i) for i in phns])
|
||||
tones.append(tns)
|
||||
# word2ph.append(len(phns))
|
||||
# phones = [post_replace_ph(i) for i in phones]
|
||||
|
||||
word2ph = []
|
||||
for token, phoneme in zip(tokens, phones):
|
||||
phone_len = len(phoneme)
|
||||
word_len = len(token)
|
||||
|
||||
aaa = distribute_phone(phone_len, word_len)
|
||||
word2ph += aaa
|
||||
|
||||
phones = ["_"] + [j for i in phones for j in i] + ["_"]
|
||||
tones = [0] + [j for i in tones for j in i] + [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)
|
||||
Reference in New Issue
Block a user