Spaces:
Running
Running
File size: 8,398 Bytes
78b6bf0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 |
import torch
import commons
import utils
from models import SynthesizerTrn
from text import cleaned_text_to_sequence, get_bert
from text.cleaner import clean_text
from text.symbols import symbols
# latest_version = "1.0"
def get_net_g(model_path: str, version: str, device: str, hps):
net_g = SynthesizerTrn(
len(symbols),
hps.data.filter_length // 2 + 1,
hps.train.segment_size // hps.data.hop_length,
n_speakers=hps.data.n_speakers,
**hps.model,
).to(device)
net_g.state_dict()
_ = net_g.eval()
if model_path.endswith(".pth") or model_path.endswith(".pt"):
_ = utils.load_checkpoint(model_path, net_g, None, skip_optimizer=True)
elif model_path.endswith(".safetensors"):
_ = utils.load_safetensors(model_path, net_g, device)
else:
raise ValueError(f"Unknown model format: {model_path}")
return net_g
def get_text(text, language_str, hps, device, style_text=None, style_weight=0.7):
# 在此处实现当前版本的get_text
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_ori = get_bert(
norm_text, word2ph, language_str, device, style_text, style_weight
)
del word2ph
assert bert_ori.shape[-1] == len(phone), phone
if language_str == "ZH":
bert = bert_ori
ja_bert = torch.zeros(1024, len(phone))
en_bert = torch.zeros(1024, len(phone))
elif language_str == "JP":
bert = torch.zeros(1024, len(phone))
ja_bert = bert_ori
en_bert = torch.zeros(1024, len(phone))
elif language_str == "EN":
bert = torch.zeros(1024, len(phone))
ja_bert = torch.zeros(1024, len(phone))
en_bert = bert_ori
else:
raise ValueError("language_str should be ZH, JP or EN")
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, en_bert, phone, tone, language
def infer(
text,
style_vec,
sdp_ratio,
noise_scale,
noise_scale_w,
length_scale,
sid: int, # In the original Bert-VITS2, its speaker_name: str, but here it's id
language,
hps,
net_g,
device,
skip_start=False,
skip_end=False,
style_text=None,
style_weight=0.7,
):
bert, ja_bert, en_bert, phones, tones, lang_ids = get_text(
text,
language,
hps,
device,
style_text=style_text,
style_weight=style_weight,
)
if skip_start:
phones = phones[3:]
tones = tones[3:]
lang_ids = lang_ids[3:]
bert = bert[:, 3:]
ja_bert = ja_bert[:, 3:]
en_bert = en_bert[:, 3:]
if skip_end:
phones = phones[:-2]
tones = tones[:-2]
lang_ids = lang_ids[:-2]
bert = bert[:, :-2]
ja_bert = ja_bert[:, :-2]
en_bert = en_bert[:, :-2]
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)
en_bert = en_bert.to(device).unsqueeze(0)
x_tst_lengths = torch.LongTensor([phones.size(0)]).to(device)
style_vec = torch.from_numpy(style_vec).to(device).unsqueeze(0)
del phones
sid_tensor = torch.LongTensor([sid]).to(device)
audio = (
net_g.infer(
x_tst,
x_tst_lengths,
sid_tensor,
tones,
lang_ids,
bert,
ja_bert,
en_bert,
style_vec=style_vec,
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,
sid_tensor,
ja_bert,
en_bert,
style_vec,
) # , emo
if torch.cuda.is_available():
torch.cuda.empty_cache()
return audio
def infer_multilang(
text,
style_vec,
sdp_ratio,
noise_scale,
noise_scale_w,
length_scale,
sid,
language,
hps,
net_g,
device,
skip_start=False,
skip_end=False,
):
bert, ja_bert, en_bert, phones, tones, lang_ids = [], [], [], [], [], []
# emo = get_emo_(reference_audio, emotion, sid)
# if isinstance(reference_audio, np.ndarray):
# emo = get_clap_audio_feature(reference_audio, device)
# else:
# emo = get_clap_text_feature(emotion, device)
# emo = torch.squeeze(emo, dim=1)
for idx, (txt, lang) in enumerate(zip(text, language)):
_skip_start = (idx != 0) or (skip_start and idx == 0)
_skip_end = (idx != len(language) - 1) or skip_end
(
temp_bert,
temp_ja_bert,
temp_en_bert,
temp_phones,
temp_tones,
temp_lang_ids,
) = get_text(txt, lang, hps, device)
if _skip_start:
temp_bert = temp_bert[:, 3:]
temp_ja_bert = temp_ja_bert[:, 3:]
temp_en_bert = temp_en_bert[:, 3:]
temp_phones = temp_phones[3:]
temp_tones = temp_tones[3:]
temp_lang_ids = temp_lang_ids[3:]
if _skip_end:
temp_bert = temp_bert[:, :-2]
temp_ja_bert = temp_ja_bert[:, :-2]
temp_en_bert = temp_en_bert[:, :-2]
temp_phones = temp_phones[:-2]
temp_tones = temp_tones[:-2]
temp_lang_ids = temp_lang_ids[:-2]
bert.append(temp_bert)
ja_bert.append(temp_ja_bert)
en_bert.append(temp_en_bert)
phones.append(temp_phones)
tones.append(temp_tones)
lang_ids.append(temp_lang_ids)
bert = torch.concatenate(bert, dim=1)
ja_bert = torch.concatenate(ja_bert, dim=1)
en_bert = torch.concatenate(en_bert, dim=1)
phones = torch.concatenate(phones, dim=0)
tones = torch.concatenate(tones, dim=0)
lang_ids = torch.concatenate(lang_ids, dim=0)
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)
en_bert = en_bert.to(device).unsqueeze(0)
# emo = emo.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,
en_bert,
style_vec=style_vec,
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,
ja_bert,
en_bert,
) # , emo
if torch.cuda.is_available():
torch.cuda.empty_cache()
return audio
|