Julius8888's picture
Upload 226 files
bc4f3f8 verified
"""
1.0.1 版本兼容
https://github.com/fishaudio/Bert-VITS2/releases/tag/1.0.1
"""
import torch
import commons
from .text.cleaner import clean_text
from .text import cleaned_text_to_sequence
from oldVersion.V111.text import get_bert
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 = torch.LongTensor(phone)
tone = torch.LongTensor(tone)
language = torch.LongTensor(language)
return bert, phone, tone, language
def infer(
text,
sdp_ratio,
noise_scale,
noise_scale_w,
length_scale,
sid,
hps,
net_g,
device,
):
bert, phones, tones, lang_ids = get_text(text, "ZH", 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)
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,
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, tones, lang_ids, bert, x_tst_lengths, speakers
if torch.cuda.is_available():
torch.cuda.empty_cache()
return audio