File size: 13,282 Bytes
b15e31b | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | import traceback
import logging
logger = logging.getLogger(__name__)
import numpy as np
import soundfile as sf
import torch
from io import BytesIO
from infer.lib.audio import load_audio, wav2
from infer.lib.infer_pack.models import (
SynthesizerTrnMs256NSFsid,
SynthesizerTrnMs256NSFsid_nono,
SynthesizerTrnMs768NSFsid,
SynthesizerTrnMs768NSFsid_nono,
)
from infer.modules.vc.pipeline import Pipeline
from infer.modules.vc.utils import *
# 导入彩色日志
try:
from lib.logger import log
except ImportError:
log = None
class VC:
def __init__(self, config):
self.n_spk = None
self.tgt_sr = None
self.net_g = None
self.pipeline = None
self.cpt = None
self.version = None
self.if_f0 = None
self.version = None
self.hubert_model = None
self.config = config
def get_vc(self, sid, *to_return_protect):
logger.info("Get sid: " + sid)
if log:
log.model(f"获取模型: {sid}")
to_return_protect0 = {
"visible": self.if_f0 != 0,
"value": (
to_return_protect[0] if self.if_f0 != 0 and to_return_protect else 0.5
),
"__type__": "update",
}
to_return_protect1 = {
"visible": self.if_f0 != 0,
"value": (
to_return_protect[1] if self.if_f0 != 0 and to_return_protect else 0.33
),
"__type__": "update",
}
if sid == "" or sid == []:
if (
self.hubert_model is not None
): # 考虑到轮询, 需要加个判断看是否 sid 是由有模型切换到无模型的
logger.info("Clean model cache")
if log:
log.detail("清理模型缓存...")
del (self.net_g, self.n_spk, self.hubert_model, self.tgt_sr) # ,cpt
self.hubert_model = self.net_g = self.n_spk = self.hubert_model = (
self.tgt_sr
) = None
if torch.cuda.is_available():
torch.cuda.empty_cache()
if log:
log.detail("已清理CUDA缓存")
###楼下不这么折腾清理不干净
self.if_f0 = self.cpt.get("f0", 1)
self.version = self.cpt.get("version", "v1")
if self.version == "v1":
if self.if_f0 == 1:
self.net_g = SynthesizerTrnMs256NSFsid(
*self.cpt["config"], is_half=self.config.is_half
)
else:
self.net_g = SynthesizerTrnMs256NSFsid_nono(*self.cpt["config"])
elif self.version == "v2":
if self.if_f0 == 1:
self.net_g = SynthesizerTrnMs768NSFsid(
*self.cpt["config"], is_half=self.config.is_half
)
else:
self.net_g = SynthesizerTrnMs768NSFsid_nono(*self.cpt["config"])
del self.net_g, self.cpt
if torch.cuda.is_available():
torch.cuda.empty_cache()
return (
{"visible": False, "__type__": "update"},
{
"visible": True,
"value": to_return_protect0,
"__type__": "update",
},
{
"visible": True,
"value": to_return_protect1,
"__type__": "update",
},
"",
"",
)
person = f'{os.getenv("weight_root")}/{sid}'
logger.info(f"Loading: {person}")
if log:
log.model(f"加载模型文件: {person}")
self.cpt = torch.load(person, map_location="cpu", weights_only=False)
self.tgt_sr = self.cpt["config"][-1]
self.cpt["config"][-3] = self.cpt["weight"]["emb_g.weight"].shape[0] # n_spk
self.if_f0 = self.cpt.get("f0", 1)
self.version = self.cpt.get("version", "v1")
if log:
log.config(f"模型版本: {self.version}")
log.config(f"目标采样率: {self.tgt_sr} Hz")
log.config(f"F0支持: {'是' if self.if_f0 else '否'}")
synthesizer_class = {
("v1", 1): SynthesizerTrnMs256NSFsid,
("v1", 0): SynthesizerTrnMs256NSFsid_nono,
("v2", 1): SynthesizerTrnMs768NSFsid,
("v2", 0): SynthesizerTrnMs768NSFsid_nono,
}
if log:
log.detail(f"选择合成器: {synthesizer_class.get((self.version, self.if_f0), SynthesizerTrnMs256NSFsid).__name__}")
self.net_g = synthesizer_class.get(
(self.version, self.if_f0), SynthesizerTrnMs256NSFsid
)(*self.cpt["config"], is_half=self.config.is_half)
del self.net_g.enc_q
self.net_g.load_state_dict(self.cpt["weight"], strict=False)
self.net_g.eval().to(self.config.device)
if self.config.is_half:
self.net_g = self.net_g.half()
if log:
log.detail("使用半精度模式")
else:
self.net_g = self.net_g.float()
if log:
log.detail("使用全精度模式")
if log:
log.progress("初始化推理管道...")
self.pipeline = Pipeline(self.tgt_sr, self.config)
n_spk = self.cpt["config"][-3]
if log:
log.config(f"说话人数量: {n_spk}")
index = {"value": get_index_path_from_model(sid), "__type__": "update"}
logger.info("Select index: " + index["value"])
if log:
log.model(f"选择索引: {index['value']}")
log.success("模型加载完成")
return (
(
{"visible": True, "maximum": n_spk, "__type__": "update"},
to_return_protect0,
to_return_protect1,
index,
index,
)
if to_return_protect
else {"visible": True, "maximum": n_spk, "__type__": "update"}
)
def vc_single(
self,
sid,
input_audio_path,
f0_up_key,
f0_file,
f0_method,
file_index,
file_index2,
index_rate,
filter_radius,
resample_sr,
rms_mix_rate,
protect,
):
if input_audio_path is None:
return "You need to upload an audio", None
if log:
log.progress("开始单文件人声转换...")
log.audio(f"输入音频: {input_audio_path}")
log.config(f"音调偏移: {f0_up_key} 半音")
log.config(f"F0方法: {f0_method}")
log.config(f"索引率: {index_rate}")
log.config(f"滤波半径: {filter_radius}")
log.config(f"RMS混合率: {rms_mix_rate}")
log.config(f"保护系数: {protect}")
f0_up_key = int(f0_up_key)
try:
if log:
log.detail("加载音频文件...")
audio = load_audio(input_audio_path, 16000)
audio_max = np.abs(audio).max() / 0.95
if audio_max > 1:
audio /= audio_max
if log:
log.detail(f"音频归一化: 峰值={audio_max:.4f}")
if log:
log.detail(f"音频长度: {len(audio)} 样本 ({len(audio)/16000:.2f} 秒)")
times = [0, 0, 0]
if self.hubert_model is None:
if log:
log.model("加载HuBERT模型...")
self.hubert_model = load_hubert(self.config)
if log:
log.success("HuBERT模型加载完成")
if file_index:
file_index = (
file_index.strip(" ")
.strip('"')
.strip("\n")
.strip('"')
.strip(" ")
.replace("trained", "added")
)
elif file_index2:
file_index = file_index2
else:
file_index = "" # 防止小白写错，自动帮他替换掉
if log and file_index:
log.model(f"使用索引文件: {file_index}")
if log:
log.progress("执行推理管道...")
audio_opt = self.pipeline.pipeline(
self.hubert_model,
self.net_g,
sid,
audio,
input_audio_path,
times,
f0_up_key,
f0_method,
file_index,
index_rate,
self.if_f0,
filter_radius,
self.tgt_sr,
resample_sr,
rms_mix_rate,
self.version,
protect,
f0_file,
)
if self.tgt_sr != resample_sr >= 16000:
tgt_sr = resample_sr
else:
tgt_sr = self.tgt_sr
index_info = (
"Index:\n%s." % file_index
if os.path.exists(file_index)
else "Index not used."
)
if log:
log.success("推理完成")
log.detail(f"NPY时间: {times[0]:.2f}s, F0时间: {times[1]:.2f}s, 推理时间: {times[2]:.2f}s")
log.audio(f"输出采样率: {tgt_sr} Hz")
log.audio(f"输出长度: {len(audio_opt)} 样本")
return (
"Success.\n%s\nTime:\nnpy: %.2fs, f0: %.2fs, infer: %.2fs."
% (index_info, *times),
(tgt_sr, audio_opt),
)
except:
info = traceback.format_exc()
logger.warning(info)
if log:
log.error(f"转换失败:\n{info}")
return info, (None, None)
def vc_multi(
self,
sid,
dir_path,
opt_root,
paths,
f0_up_key,
f0_method,
file_index,
file_index2,
index_rate,
filter_radius,
resample_sr,
rms_mix_rate,
protect,
format1,
):
try:
dir_path = (
dir_path.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
) # 防止小白拷路径头尾带了空格和"和回车
opt_root = opt_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
os.makedirs(opt_root, exist_ok=True)
try:
if dir_path != "":
paths = [
os.path.join(dir_path, name) for name in os.listdir(dir_path)
]
else:
paths = [path.name for path in paths]
except:
traceback.print_exc()
paths = [path.name for path in paths]
infos = []
for path in paths:
info, opt = self.vc_single(
sid,
path,
f0_up_key,
None,
f0_method,
file_index,
file_index2,
# file_big_npy,
index_rate,
filter_radius,
resample_sr,
rms_mix_rate,
protect,
)
if "Success" in info:
try:
tgt_sr, audio_opt = opt
if format1 in ["wav", "flac"]:
sf.write(
"%s/%s.%s"
% (opt_root, os.path.basename(path), format1),
audio_opt,
tgt_sr,
)
else:
path = "%s/%s.%s" % (
opt_root,
os.path.basename(path),
format1,
)
with BytesIO() as wavf:
sf.write(wavf, audio_opt, tgt_sr, format="wav")
wavf.seek(0, 0)
with open(path, "wb") as outf:
wav2(wavf, outf, format1)
except:
info += traceback.format_exc()
infos.append("%s->%s" % (os.path.basename(path), info))
yield "\n".join(infos)
yield "\n".join(infos)
except:
yield traceback.format_exc()
|