File size: 14,531 Bytes
6ff2047 |
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 |
import os, sys, torch, warnings, pdb
now_dir = os.getcwd()
sys.path.append(now_dir)
from json import load as ll
warnings.filterwarnings("ignore")
import librosa
import importlib
import numpy as np
import hashlib, math
from tqdm import tqdm
from lib.uvr5_pack.lib_v5 import spec_utils
from lib.uvr5_pack.utils import _get_name_params, inference
from lib.uvr5_pack.lib_v5.model_param_init import ModelParameters
import soundfile as sf
from lib.uvr5_pack.lib_v5.nets_new import CascadedNet
from lib.uvr5_pack.lib_v5 import nets_61968KB as nets
class _audio_pre_:
def __init__(self, agg, model_path, device, is_half):
self.model_path = model_path
self.device = device
self.data = {
# Processing Options
"postprocess": False,
"tta": False,
# Constants
"window_size": 512,
"agg": agg,
"high_end_process": "mirroring",
}
mp = ModelParameters("lib/uvr5_pack/lib_v5/modelparams/4band_v2.json")
model = nets.CascadedASPPNet(mp.param["bins"] * 2)
cpk = torch.load(model_path, map_location="cpu")
model.load_state_dict(cpk)
model.eval()
if is_half:
model = model.half().to(device)
else:
model = model.to(device)
self.mp = mp
self.model = model
def _path_audio_(self, music_file, ins_root=None, vocal_root=None, format="flac"):
if ins_root is None and vocal_root is None:
return "No save root."
name = os.path.basename(music_file)
if ins_root is not None:
os.makedirs(ins_root, exist_ok=True)
if vocal_root is not None:
os.makedirs(vocal_root, exist_ok=True)
X_wave, y_wave, X_spec_s, y_spec_s = {}, {}, {}, {}
bands_n = len(self.mp.param["band"])
# print(bands_n)
for d in range(bands_n, 0, -1):
bp = self.mp.param["band"][d]
if d == bands_n: # high-end band
(
X_wave[d],
_,
) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
music_file,
bp["sr"],
False,
dtype=np.float32,
res_type=bp["res_type"],
)
if X_wave[d].ndim == 1:
X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
else: # lower bands
X_wave[d] = librosa.core.resample(
X_wave[d + 1],
self.mp.param["band"][d + 1]["sr"],
bp["sr"],
res_type=bp["res_type"],
)
# Stft of wave source
X_spec_s[d] = spec_utils.wave_to_spectrogram_mt(
X_wave[d],
bp["hl"],
bp["n_fft"],
self.mp.param["mid_side"],
self.mp.param["mid_side_b2"],
self.mp.param["reverse"],
)
# pdb.set_trace()
if d == bands_n and self.data["high_end_process"] != "none":
input_high_end_h = (bp["n_fft"] // 2 - bp["crop_stop"]) + (
self.mp.param["pre_filter_stop"] - self.mp.param["pre_filter_start"]
)
input_high_end = X_spec_s[d][
:, bp["n_fft"] // 2 - input_high_end_h : bp["n_fft"] // 2, :
]
X_spec_m = spec_utils.combine_spectrograms(X_spec_s, self.mp)
aggresive_set = float(self.data["agg"] / 100)
aggressiveness = {
"value": aggresive_set,
"split_bin": self.mp.param["band"][1]["crop_stop"],
}
with torch.no_grad():
pred, X_mag, X_phase = inference(
X_spec_m, self.device, self.model, aggressiveness, self.data
)
# Postprocess
if self.data["postprocess"]:
pred_inv = np.clip(X_mag - pred, 0, np.inf)
pred = spec_utils.mask_silence(pred, pred_inv)
y_spec_m = pred * X_phase
v_spec_m = X_spec_m - y_spec_m
if ins_root is not None:
if self.data["high_end_process"].startswith("mirroring"):
input_high_end_ = spec_utils.mirroring(
self.data["high_end_process"], y_spec_m, input_high_end, self.mp
)
wav_instrument = spec_utils.cmb_spectrogram_to_wave(
y_spec_m, self.mp, input_high_end_h, input_high_end_
)
else:
wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
print("%s instruments done" % name)
if format in ["wav", "flac"]:
sf.write(
os.path.join(
ins_root,
"instrument_{}_{}.{}".format(name, self.data["agg"], format),
),
(np.array(wav_instrument) * 32768).astype("int16"),
self.mp.param["sr"],
) #
else:
path = os.path.join(
ins_root, "instrument_{}_{}.wav".format(name, self.data["agg"])
)
sf.write(
path,
(np.array(wav_instrument) * 32768).astype("int16"),
self.mp.param["sr"],
)
if os.path.exists(path):
os.system(
"ffmpeg -i %s -vn %s -q:a 2 -y"
% (path, path[:-4] + ".%s" % format)
)
if vocal_root is not None:
if self.data["high_end_process"].startswith("mirroring"):
input_high_end_ = spec_utils.mirroring(
self.data["high_end_process"], v_spec_m, input_high_end, self.mp
)
wav_vocals = spec_utils.cmb_spectrogram_to_wave(
v_spec_m, self.mp, input_high_end_h, input_high_end_
)
else:
wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
print("%s vocals done" % name)
if format in ["wav", "flac"]:
sf.write(
os.path.join(
vocal_root,
"vocal_{}_{}.{}".format(name, self.data["agg"], format),
),
(np.array(wav_vocals) * 32768).astype("int16"),
self.mp.param["sr"],
)
else:
path = os.path.join(
vocal_root, "vocal_{}_{}.wav".format(name, self.data["agg"])
)
sf.write(
path,
(np.array(wav_vocals) * 32768).astype("int16"),
self.mp.param["sr"],
)
if os.path.exists(path):
os.system(
"ffmpeg -i %s -vn %s -q:a 2 -y"
% (path, path[:-4] + ".%s" % format)
)
class _audio_pre_new:
def __init__(self, agg, model_path, device, is_half):
self.model_path = model_path
self.device = device
self.data = {
# Processing Options
"postprocess": False,
"tta": False,
# Constants
"window_size": 512,
"agg": agg,
"high_end_process": "mirroring",
}
mp = ModelParameters("lib/uvr5_pack/lib_v5/modelparams/4band_v3.json")
nout = 64 if "DeReverb" in model_path else 48
model = CascadedNet(mp.param["bins"] * 2, nout)
cpk = torch.load(model_path, map_location="cpu")
model.load_state_dict(cpk)
model.eval()
if is_half:
model = model.half().to(device)
else:
model = model.to(device)
self.mp = mp
self.model = model
def _path_audio_(
self, music_file, vocal_root=None, ins_root=None, format="flac"
): # 3个VR模型vocal和ins是反的
if ins_root is None and vocal_root is None:
return "No save root."
name = os.path.basename(music_file)
if ins_root is not None:
os.makedirs(ins_root, exist_ok=True)
if vocal_root is not None:
os.makedirs(vocal_root, exist_ok=True)
X_wave, y_wave, X_spec_s, y_spec_s = {}, {}, {}, {}
bands_n = len(self.mp.param["band"])
# print(bands_n)
for d in range(bands_n, 0, -1):
bp = self.mp.param["band"][d]
if d == bands_n: # high-end band
(
X_wave[d],
_,
) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
music_file,
bp["sr"],
False,
dtype=np.float32,
res_type=bp["res_type"],
)
if X_wave[d].ndim == 1:
X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
else: # lower bands
X_wave[d] = librosa.core.resample(
X_wave[d + 1],
self.mp.param["band"][d + 1]["sr"],
bp["sr"],
res_type=bp["res_type"],
)
# Stft of wave source
X_spec_s[d] = spec_utils.wave_to_spectrogram_mt(
X_wave[d],
bp["hl"],
bp["n_fft"],
self.mp.param["mid_side"],
self.mp.param["mid_side_b2"],
self.mp.param["reverse"],
)
# pdb.set_trace()
if d == bands_n and self.data["high_end_process"] != "none":
input_high_end_h = (bp["n_fft"] // 2 - bp["crop_stop"]) + (
self.mp.param["pre_filter_stop"] - self.mp.param["pre_filter_start"]
)
input_high_end = X_spec_s[d][
:, bp["n_fft"] // 2 - input_high_end_h : bp["n_fft"] // 2, :
]
X_spec_m = spec_utils.combine_spectrograms(X_spec_s, self.mp)
aggresive_set = float(self.data["agg"] / 100)
aggressiveness = {
"value": aggresive_set,
"split_bin": self.mp.param["band"][1]["crop_stop"],
}
with torch.no_grad():
pred, X_mag, X_phase = inference(
X_spec_m, self.device, self.model, aggressiveness, self.data
)
# Postprocess
if self.data["postprocess"]:
pred_inv = np.clip(X_mag - pred, 0, np.inf)
pred = spec_utils.mask_silence(pred, pred_inv)
y_spec_m = pred * X_phase
v_spec_m = X_spec_m - y_spec_m
if ins_root is not None:
if self.data["high_end_process"].startswith("mirroring"):
input_high_end_ = spec_utils.mirroring(
self.data["high_end_process"], y_spec_m, input_high_end, self.mp
)
wav_instrument = spec_utils.cmb_spectrogram_to_wave(
y_spec_m, self.mp, input_high_end_h, input_high_end_
)
else:
wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
print("%s instruments done" % name)
if format in ["wav", "flac"]:
sf.write(
os.path.join(
ins_root,
"instrument_{}_{}.{}".format(name, self.data["agg"], format),
),
(np.array(wav_instrument) * 32768).astype("int16"),
self.mp.param["sr"],
) #
else:
path = os.path.join(
ins_root, "instrument_{}_{}.wav".format(name, self.data["agg"])
)
sf.write(
path,
(np.array(wav_instrument) * 32768).astype("int16"),
self.mp.param["sr"],
)
if os.path.exists(path):
os.system(
"ffmpeg -i %s -vn %s -q:a 2 -y"
% (path, path[:-4] + ".%s" % format)
)
if vocal_root is not None:
if self.data["high_end_process"].startswith("mirroring"):
input_high_end_ = spec_utils.mirroring(
self.data["high_end_process"], v_spec_m, input_high_end, self.mp
)
wav_vocals = spec_utils.cmb_spectrogram_to_wave(
v_spec_m, self.mp, input_high_end_h, input_high_end_
)
else:
wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
print("%s vocals done" % name)
if format in ["wav", "flac"]:
sf.write(
os.path.join(
vocal_root,
"vocal_{}_{}.{}".format(name, self.data["agg"], format),
),
(np.array(wav_vocals) * 32768).astype("int16"),
self.mp.param["sr"],
)
else:
path = os.path.join(
vocal_root, "vocal_{}_{}.wav".format(name, self.data["agg"])
)
sf.write(
path,
(np.array(wav_vocals) * 32768).astype("int16"),
self.mp.param["sr"],
)
if os.path.exists(path):
os.system(
"ffmpeg -i %s -vn %s -q:a 2 -y"
% (path, path[:-4] + ".%s" % format)
)
if __name__ == "__main__":
device = "cuda"
is_half = True
# model_path = "uvr5_weights/2_HP-UVR.pth"
# model_path = "uvr5_weights/VR-DeEchoDeReverb.pth"
# model_path = "uvr5_weights/VR-DeEchoNormal.pth"
model_path = "uvr5_weights/DeEchoNormal.pth"
# pre_fun = _audio_pre_(model_path=model_path, device=device, is_half=True,agg=10)
pre_fun = _audio_pre_new(model_path=model_path, device=device, is_half=True, agg=10)
audio_path = "雪雪伴奏对消HP5.wav"
save_path = "opt"
pre_fun._path_audio_(audio_path, save_path, save_path)
|