File size: 5,214 Bytes
060d192 |
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 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
"""
1.1.1版本兼容
https://github.com/fishaudio/Bert-VITS2/releases/tag/1.1.1
"""
import torch
import commons
from .text.cleaner import clean_text, clean_text_fix
from .text import cleaned_text_to_sequence
from .text import get_bert, get_bert_fix
def get_text(text, language_str, hps, device):
norm_text, phone, tone, word2ph = clean_text(text, language_str)
phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str)
if hps.data.add_blank:
phone = commons.intersperse(phone, 0)
tone = commons.intersperse(tone, 0)
language = commons.intersperse(language, 0)
for i in range(len(word2ph)):
word2ph[i] = word2ph[i] * 2
word2ph[0] += 1
bert = get_bert(norm_text, word2ph, language_str, device)
del word2ph
assert bert.shape[-1] == len(phone), phone
if language_str == "ZH":
bert = bert
ja_bert = torch.zeros(768, len(phone))
elif language_str == "JP":
ja_bert = bert
bert = torch.zeros(1024, len(phone))
else:
bert = torch.zeros(1024, len(phone))
ja_bert = torch.zeros(768, len(phone))
assert bert.shape[-1] == len(
phone
), f"Bert seq len {bert.shape[-1]} != {len(phone)}"
phone = torch.LongTensor(phone)
tone = torch.LongTensor(tone)
language = torch.LongTensor(language)
return bert, ja_bert, phone, tone, language
def get_text_fix(text, language_str, hps, device):
norm_text, phone, tone, word2ph = clean_text_fix(text, language_str)
phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str)
if hps.data.add_blank:
phone = commons.intersperse(phone, 0)
tone = commons.intersperse(tone, 0)
language = commons.intersperse(language, 0)
for i in range(len(word2ph)):
word2ph[i] = word2ph[i] * 2
word2ph[0] += 1
bert = get_bert_fix(norm_text, word2ph, language_str, device)
del word2ph
assert bert.shape[-1] == len(phone), phone
if language_str == "ZH":
bert = bert
ja_bert = torch.zeros(768, len(phone))
elif language_str == "JP":
ja_bert = bert
bert = torch.zeros(1024, len(phone))
else:
bert = torch.zeros(1024, len(phone))
ja_bert = torch.zeros(768, len(phone))
assert bert.shape[-1] == len(
phone
), f"Bert seq len {bert.shape[-1]} != {len(phone)}"
phone = torch.LongTensor(phone)
tone = torch.LongTensor(tone)
language = torch.LongTensor(language)
return bert, ja_bert, phone, tone, language
def infer(
text,
sdp_ratio,
noise_scale,
noise_scale_w,
length_scale,
sid,
language,
hps,
net_g,
device,
):
bert, ja_bert, phones, tones, lang_ids = get_text(text, language, hps, device)
with torch.no_grad():
x_tst = phones.to(device).unsqueeze(0)
tones = tones.to(device).unsqueeze(0)
lang_ids = lang_ids.to(device).unsqueeze(0)
bert = bert.to(device).unsqueeze(0)
ja_bert = ja_bert.to(device).unsqueeze(0)
x_tst_lengths = torch.LongTensor([phones.size(0)]).to(device)
del phones
speakers = torch.LongTensor([hps.data.spk2id[sid]]).to(device)
audio = (
net_g.infer(
x_tst,
x_tst_lengths,
speakers,
tones,
lang_ids,
bert,
ja_bert,
sdp_ratio=sdp_ratio,
noise_scale=noise_scale,
noise_scale_w=noise_scale_w,
length_scale=length_scale,
)[0][0, 0]
.data.cpu()
.float()
.numpy()
)
del x_tst, x_tst_lengths, speakers, tones, lang_ids, bert, ja_bert
if torch.cuda.is_available():
torch.cuda.empty_cache()
return audio
def infer_fix(
text,
sdp_ratio,
noise_scale,
noise_scale_w,
length_scale,
sid,
language,
hps,
net_g,
device,
):
bert, ja_bert, phones, tones, lang_ids = get_text_fix(text, language, hps, device)
with torch.no_grad():
x_tst = phones.to(device).unsqueeze(0)
tones = tones.to(device).unsqueeze(0)
lang_ids = lang_ids.to(device).unsqueeze(0)
bert = bert.to(device).unsqueeze(0)
ja_bert = ja_bert.to(device).unsqueeze(0)
x_tst_lengths = torch.LongTensor([phones.size(0)]).to(device)
del phones
speakers = torch.LongTensor([hps.data.spk2id[sid]]).to(device)
audio = (
net_g.infer(
x_tst,
x_tst_lengths,
speakers,
tones,
lang_ids,
bert,
ja_bert,
sdp_ratio=sdp_ratio,
noise_scale=noise_scale,
noise_scale_w=noise_scale_w,
length_scale=length_scale,
)[0][0, 0]
.data.cpu()
.float()
.numpy()
)
del x_tst, x_tst_lengths, speakers, tones, lang_ids, bert, ja_bert
if torch.cuda.is_available():
torch.cuda.empty_cache()
return audio
|