format
This commit is contained in:
parent
3c7f1f1407
commit
58e32b6def
@ -1,9 +1,10 @@
|
||||
import os
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
import torch
|
||||
from multiprocessing import cpu_count
|
||||
|
||||
import torch
|
||||
|
||||
|
||||
def use_fp32_config():
|
||||
for config_file in [
|
||||
@ -198,6 +199,3 @@ class Config:
|
||||
except:
|
||||
pass
|
||||
return x_pad, x_query, x_center, x_max
|
||||
|
||||
|
||||
defaultconfig = Config()
|
||||
|
32
gui_v1.py
32
gui_v1.py
@ -1,4 +1,6 @@
|
||||
import os, sys, pdb
|
||||
import os
|
||||
import pdb
|
||||
import sys
|
||||
|
||||
os.environ["OMP_NUM_THREADS"] = "2"
|
||||
if sys.platform == "darwin":
|
||||
@ -16,7 +18,8 @@ class Harvest(multiprocessing.Process):
|
||||
self.opt_q = opt_q
|
||||
|
||||
def run(self):
|
||||
import numpy as np, pyworld
|
||||
import numpy as np
|
||||
import pyworld
|
||||
|
||||
while 1:
|
||||
idx, x, res_f0, n_cpu, ts = self.inp_q.get()
|
||||
@ -33,21 +36,26 @@ class Harvest(multiprocessing.Process):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from multiprocessing import Queue
|
||||
from queue import Empty
|
||||
import numpy as np
|
||||
import multiprocessing
|
||||
import traceback, re
|
||||
import json
|
||||
import PySimpleGUI as sg
|
||||
import sounddevice as sd
|
||||
import multiprocessing
|
||||
import re
|
||||
import threading
|
||||
import time
|
||||
import traceback
|
||||
from multiprocessing import Queue, cpu_count
|
||||
from queue import Empty
|
||||
|
||||
import librosa
|
||||
import noisereduce as nr
|
||||
from multiprocessing import cpu_count
|
||||
import librosa, torch, time, threading
|
||||
import numpy as np
|
||||
import PySimpleGUI as sg
|
||||
import rvc_for_realtime
|
||||
import sounddevice as sd
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
import torchaudio.transforms as tat
|
||||
|
||||
from i18n import I18nAuto
|
||||
import rvc_for_realtime
|
||||
|
||||
i18n = I18nAuto()
|
||||
device = rvc_for_realtime.config.device
|
||||
|
@ -1,5 +1,5 @@
|
||||
import locale
|
||||
import json
|
||||
import locale
|
||||
import os
|
||||
|
||||
|
||||
|
@ -1,7 +1,6 @@
|
||||
import ast
|
||||
import glob
|
||||
import json
|
||||
|
||||
from collections import OrderedDict
|
||||
|
||||
|
||||
|
@ -1,5 +1,5 @@
|
||||
import librosa
|
||||
import ffmpeg
|
||||
import librosa
|
||||
import numpy as np
|
||||
|
||||
|
||||
|
@ -1,12 +1,12 @@
|
||||
import copy
|
||||
import math
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch import nn
|
||||
from torch.nn import functional as F
|
||||
|
||||
from infer.lib.infer_pack import commons
|
||||
from infer.lib.infer_pack import modules
|
||||
from infer.lib.infer_pack import commons, modules
|
||||
from infer.lib.infer_pack.modules import LayerNorm
|
||||
|
||||
|
||||
|
@ -1,4 +1,5 @@
|
||||
import math
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch import nn
|
||||
|
@ -1,17 +1,17 @@
|
||||
import math, pdb, os
|
||||
import math
|
||||
import os
|
||||
import pdb
|
||||
from time import time as ttime
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch import nn
|
||||
from torch.nn import AvgPool1d, Conv1d, Conv2d, ConvTranspose1d
|
||||
from torch.nn import functional as F
|
||||
from infer.lib.infer_pack import modules
|
||||
from infer.lib.infer_pack import attentions
|
||||
from infer.lib.infer_pack import commons
|
||||
from infer.lib.infer_pack.commons import init_weights, get_padding
|
||||
from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
|
||||
from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
|
||||
from infer.lib.infer_pack.commons import init_weights
|
||||
import numpy as np
|
||||
from infer.lib.infer_pack import commons
|
||||
from torch.nn.utils import remove_weight_norm, spectral_norm, weight_norm
|
||||
|
||||
from infer.lib.infer_pack import attentions, commons, modules
|
||||
from infer.lib.infer_pack.commons import get_padding, init_weights
|
||||
|
||||
|
||||
class TextEncoder256(nn.Module):
|
||||
|
@ -1,17 +1,17 @@
|
||||
import math, pdb, os
|
||||
import math
|
||||
import os
|
||||
import pdb
|
||||
from time import time as ttime
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch import nn
|
||||
from torch.nn import AvgPool1d, Conv1d, Conv2d, ConvTranspose1d
|
||||
from torch.nn import functional as F
|
||||
from infer.lib.infer_pack import modules
|
||||
from infer.lib.infer_pack import attentions
|
||||
from infer.lib.infer_pack import commons
|
||||
from infer.lib.infer_pack.commons import init_weights, get_padding
|
||||
from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
|
||||
from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
|
||||
from infer.lib.infer_pack.commons import init_weights
|
||||
import numpy as np
|
||||
from infer.lib.infer_pack import commons
|
||||
from torch.nn.utils import remove_weight_norm, spectral_norm, weight_norm
|
||||
|
||||
from infer.lib.infer_pack import attentions, commons, modules
|
||||
from infer.lib.infer_pack.commons import get_padding, init_weights
|
||||
|
||||
|
||||
class TextEncoder256(nn.Module):
|
||||
|
@ -1,19 +1,18 @@
|
||||
import copy
|
||||
import math
|
||||
|
||||
import numpy as np
|
||||
import scipy
|
||||
import torch
|
||||
from torch import nn
|
||||
from torch.nn import AvgPool1d, Conv1d, Conv2d, ConvTranspose1d
|
||||
from torch.nn import functional as F
|
||||
|
||||
from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
|
||||
from torch.nn.utils import weight_norm, remove_weight_norm
|
||||
from torch.nn.utils import remove_weight_norm, weight_norm
|
||||
|
||||
from infer.lib.infer_pack import commons
|
||||
from infer.lib.infer_pack.commons import init_weights, get_padding
|
||||
from infer.lib.infer_pack.commons import get_padding, init_weights
|
||||
from infer.lib.infer_pack.transforms import piecewise_rational_quadratic_transform
|
||||
|
||||
|
||||
LRELU_SLOPE = 0.1
|
||||
|
||||
|
||||
|
@ -1,6 +1,7 @@
|
||||
from infer.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
|
||||
import pyworld
|
||||
import numpy as np
|
||||
import pyworld
|
||||
|
||||
from infer.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
|
||||
|
||||
|
||||
class DioF0Predictor(F0Predictor):
|
||||
|
@ -1,6 +1,7 @@
|
||||
from infer.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
|
||||
import pyworld
|
||||
import numpy as np
|
||||
import pyworld
|
||||
|
||||
from infer.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
|
||||
|
||||
|
||||
class HarvestF0Predictor(F0Predictor):
|
||||
|
@ -1,6 +1,7 @@
|
||||
from infer.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
|
||||
import parselmouth
|
||||
import numpy as np
|
||||
import parselmouth
|
||||
|
||||
from infer.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
|
||||
|
||||
|
||||
class PMF0Predictor(F0Predictor):
|
||||
|
@ -1,6 +1,6 @@
|
||||
import onnxruntime
|
||||
import librosa
|
||||
import numpy as np
|
||||
import onnxruntime
|
||||
import soundfile
|
||||
|
||||
|
||||
|
@ -1,9 +1,7 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch.nn import functional as F
|
||||
|
||||
import numpy as np
|
||||
|
||||
|
||||
DEFAULT_MIN_BIN_WIDTH = 1e-3
|
||||
DEFAULT_MIN_BIN_HEIGHT = 1e-3
|
||||
DEFAULT_MIN_DERIVATIVE = 1e-3
|
||||
|
@ -1,11 +1,11 @@
|
||||
import torch, numpy as np, pdb
|
||||
import pdb
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torch, pdb
|
||||
import numpy as np
|
||||
import torch.nn.functional as F
|
||||
from librosa.util import normalize, pad_center, tiny
|
||||
from scipy.signal import get_window
|
||||
from librosa.util import pad_center, tiny, normalize
|
||||
|
||||
|
||||
###stft codes from https://github.com/pseeth/torch-stft/blob/master/torch_stft/util.py
|
||||
@ -670,7 +670,8 @@ class RMVPE:
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import soundfile as sf, librosa
|
||||
import librosa
|
||||
import soundfile as sf
|
||||
|
||||
audio, sampling_rate = sf.read(r"C:\Users\liujing04\Desktop\Z\冬之花clip1.wav")
|
||||
if len(audio.shape) > 1:
|
||||
|
@ -1,10 +1,12 @@
|
||||
import os, traceback
|
||||
import os
|
||||
import traceback
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.utils.data
|
||||
|
||||
from infer.lib.train.mel_processing import spectrogram_torch
|
||||
from infer.lib.train.utils import load_wav_to_torch, load_filepaths_and_text
|
||||
from infer.lib.train.utils import load_filepaths_and_text, load_wav_to_torch
|
||||
|
||||
|
||||
class TextAudioLoaderMultiNSFsid(torch.utils.data.Dataset):
|
||||
|
@ -2,7 +2,6 @@ import torch
|
||||
import torch.utils.data
|
||||
from librosa.filters import mel as librosa_mel_fn
|
||||
|
||||
|
||||
MAX_WAV_VALUE = 32768.0
|
||||
|
||||
|
||||
|
@ -1,7 +1,10 @@
|
||||
import torch, traceback, os, sys
|
||||
|
||||
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
from collections import OrderedDict
|
||||
|
||||
import torch
|
||||
|
||||
from i18n.i18n import I18nAuto
|
||||
|
||||
i18n = I18nAuto()
|
||||
|
@ -1,13 +1,15 @@
|
||||
import os, traceback
|
||||
import glob
|
||||
import sys
|
||||
import argparse
|
||||
import logging
|
||||
import glob
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
import numpy as np
|
||||
from scipy.io.wavfile import read
|
||||
import torch
|
||||
from scipy.io.wavfile import read
|
||||
|
||||
MATPLOTLIB_FLAG = False
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
@ -1,8 +1,8 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
import layers
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import spec_utils
|
||||
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import layers_123821KB as layers
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import layers_123821KB as layers
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import layers_33966KB as layers
|
||||
|
||||
|
@ -1,7 +1,7 @@
|
||||
import torch
|
||||
import numpy as np
|
||||
from torch import nn
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import layers_537238KB as layers
|
||||
|
||||
|
@ -1,7 +1,7 @@
|
||||
import torch
|
||||
import numpy as np
|
||||
from torch import nn
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import layers_537238KB as layers
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import layers_123821KB as layers
|
||||
|
||||
|
@ -1,6 +1,7 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from . import layers_new
|
||||
|
||||
|
||||
|
@ -1,8 +1,12 @@
|
||||
import os, librosa
|
||||
import hashlib
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
|
||||
import librosa
|
||||
import numpy as np
|
||||
import soundfile as sf
|
||||
from tqdm import tqdm
|
||||
import json, math, hashlib
|
||||
|
||||
|
||||
def crop_center(h1, h2):
|
||||
@ -519,10 +523,11 @@ def istft(spec, hl):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import cv2
|
||||
import argparse
|
||||
import sys
|
||||
import time
|
||||
import argparse
|
||||
|
||||
import cv2
|
||||
from model_param_init import ModelParameters
|
||||
|
||||
p = argparse.ArgumentParser()
|
||||
|
@ -1,8 +1,9 @@
|
||||
import torch
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
import json
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from tqdm import tqdm
|
||||
|
||||
|
||||
def load_data(file_name: str = "./infer/lib/uvr5_pack/name_params.json") -> dict:
|
||||
with open(file_name, "r") as f:
|
||||
|
@ -1,10 +1,16 @@
|
||||
import os, traceback, sys, parselmouth
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
import parselmouth
|
||||
|
||||
now_dir = os.getcwd()
|
||||
sys.path.append(now_dir)
|
||||
from lib.audio import load_audio
|
||||
import logging
|
||||
|
||||
import numpy as np
|
||||
import pyworld
|
||||
import numpy as np, logging
|
||||
from lib.audio import load_audio
|
||||
|
||||
logging.getLogger("numba").setLevel(logging.WARNING)
|
||||
from multiprocessing import Process
|
||||
|
@ -1,10 +1,16 @@
|
||||
import os, traceback, sys, parselmouth
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
import parselmouth
|
||||
|
||||
now_dir = os.getcwd()
|
||||
sys.path.append(now_dir)
|
||||
from lib.audio import load_audio
|
||||
import logging
|
||||
|
||||
import numpy as np
|
||||
import pyworld
|
||||
import numpy as np, logging
|
||||
from lib.audio import load_audio
|
||||
|
||||
logging.getLogger("numba").setLevel(logging.WARNING)
|
||||
|
||||
|
@ -1,10 +1,16 @@
|
||||
import os, traceback, sys, parselmouth
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
import parselmouth
|
||||
|
||||
now_dir = os.getcwd()
|
||||
sys.path.append(now_dir)
|
||||
from lib.audio import load_audio
|
||||
import logging
|
||||
|
||||
import numpy as np
|
||||
import pyworld
|
||||
import numpy as np, logging
|
||||
from lib.audio import load_audio
|
||||
|
||||
logging.getLogger("numba").setLevel(logging.WARNING)
|
||||
|
||||
|
@ -1,4 +1,6 @@
|
||||
import os, sys, traceback
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
|
||||
os.environ["PYTORCH_MPS_HIGH_WATERMARK_RATIO"] = "0.0"
|
||||
@ -14,11 +16,11 @@ else:
|
||||
exp_dir = sys.argv[5]
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = str(i_gpu)
|
||||
version = sys.argv[6]
|
||||
import fairseq
|
||||
import numpy as np
|
||||
import soundfile as sf
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
import soundfile as sf
|
||||
import numpy as np
|
||||
import fairseq
|
||||
|
||||
if "privateuseone" not in device:
|
||||
device = "cpu"
|
||||
|
@ -1,4 +1,7 @@
|
||||
import sys, os, multiprocessing
|
||||
import multiprocessing
|
||||
import os
|
||||
import sys
|
||||
|
||||
from scipy import signal
|
||||
|
||||
now_dir = os.getcwd()
|
||||
@ -9,12 +12,15 @@ sr = int(sys.argv[2])
|
||||
n_p = int(sys.argv[3])
|
||||
exp_dir = sys.argv[4]
|
||||
noparallel = sys.argv[5] == "True"
|
||||
import numpy as np, os, traceback
|
||||
from lib.slicer2 import Slicer
|
||||
import librosa, traceback
|
||||
from scipy.io import wavfile
|
||||
import multiprocessing
|
||||
import os
|
||||
import traceback
|
||||
|
||||
import librosa
|
||||
import numpy as np
|
||||
from lib.audio import load_audio
|
||||
from lib.slicer2 import Slicer
|
||||
from scipy.io import wavfile
|
||||
|
||||
mutex = multiprocessing.Lock()
|
||||
f = open("%s/preprocess.log" % exp_dir, "a+")
|
||||
|
@ -1,43 +1,47 @@
|
||||
import os, sys
|
||||
import os
|
||||
import sys
|
||||
|
||||
now_dir = os.getcwd()
|
||||
sys.path.append(os.path.join(now_dir))
|
||||
|
||||
from infer.lib.train import utils
|
||||
import datetime
|
||||
|
||||
from infer.lib.train import utils
|
||||
|
||||
hps = utils.get_hparams()
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = hps.gpus.replace("-", ",")
|
||||
n_gpus = len(hps.gpus.split("-"))
|
||||
from random import shuffle, randint
|
||||
from random import randint, shuffle
|
||||
|
||||
import torch
|
||||
|
||||
torch.backends.cudnn.deterministic = False
|
||||
torch.backends.cudnn.benchmark = False
|
||||
from torch.nn import functional as F
|
||||
from torch.utils.data import DataLoader
|
||||
from torch.utils.tensorboard import SummaryWriter
|
||||
import torch.multiprocessing as mp
|
||||
import torch.distributed as dist
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
from torch.cuda.amp import autocast, GradScaler
|
||||
from infer.lib.infer_pack import commons
|
||||
from time import sleep
|
||||
from time import time as ttime
|
||||
|
||||
import torch.distributed as dist
|
||||
import torch.multiprocessing as mp
|
||||
from torch.cuda.amp import GradScaler, autocast
|
||||
from torch.nn import functional as F
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
from torch.utils.data import DataLoader
|
||||
from torch.utils.tensorboard import SummaryWriter
|
||||
|
||||
from infer.lib.infer_pack import commons
|
||||
from infer.lib.train.data_utils import (
|
||||
TextAudioLoaderMultiNSFsid,
|
||||
TextAudioLoader,
|
||||
TextAudioCollateMultiNSFsid,
|
||||
TextAudioCollate,
|
||||
DistributedBucketSampler,
|
||||
TextAudioCollate,
|
||||
TextAudioCollateMultiNSFsid,
|
||||
TextAudioLoader,
|
||||
TextAudioLoaderMultiNSFsid,
|
||||
)
|
||||
|
||||
if hps.version == "v1":
|
||||
from infer.lib.infer_pack.models import MultiPeriodDiscriminator
|
||||
from infer.lib.infer_pack.models import SynthesizerTrnMs256NSFsid as RVC_Model_f0
|
||||
from infer.lib.infer_pack.models import (
|
||||
SynthesizerTrnMs256NSFsid as RVC_Model_f0,
|
||||
SynthesizerTrnMs256NSFsid_nono as RVC_Model_nof0,
|
||||
MultiPeriodDiscriminator,
|
||||
)
|
||||
else:
|
||||
from infer.lib.infer_pack.models import (
|
||||
@ -45,10 +49,11 @@ else:
|
||||
SynthesizerTrnMs768NSFsid_nono as RVC_Model_nof0,
|
||||
MultiPeriodDiscriminatorV2 as MultiPeriodDiscriminator,
|
||||
)
|
||||
|
||||
from infer.lib.train.losses import (
|
||||
generator_loss,
|
||||
discriminator_loss,
|
||||
feature_loss,
|
||||
generator_loss,
|
||||
kl_loss,
|
||||
)
|
||||
from infer.lib.train.mel_processing import mel_spectrogram_torch, spec_to_mel_torch
|
||||
|
@ -1,12 +1,12 @@
|
||||
import os
|
||||
import warnings
|
||||
|
||||
import soundfile as sf
|
||||
import librosa
|
||||
import numpy as np
|
||||
import onnxruntime as ort
|
||||
from tqdm import tqdm
|
||||
import soundfile as sf
|
||||
import torch
|
||||
from tqdm import tqdm
|
||||
|
||||
cpu = torch.device("cpu")
|
||||
|
||||
|
@ -1,12 +1,12 @@
|
||||
import os
|
||||
import traceback
|
||||
|
||||
import torch
|
||||
import ffmpeg
|
||||
import torch
|
||||
|
||||
from configs.config import Config
|
||||
from infer.modules.uvr5.preprocess import AudioPre, AudioPreDeEcho
|
||||
from infer.modules.uvr5.mdxnet import MDXNetDereverb
|
||||
from infer.modules.uvr5.preprocess import AudioPre, AudioPreDeEcho
|
||||
|
||||
config = Config()
|
||||
|
||||
|
@ -1,16 +1,15 @@
|
||||
import os
|
||||
import torch
|
||||
|
||||
import librosa
|
||||
import numpy as np
|
||||
import soundfile as sf
|
||||
import torch
|
||||
|
||||
from infer.lib.uvr5_pack.lib_v5 import spec_utils
|
||||
from infer.lib.uvr5_pack.utils import inference
|
||||
from infer.lib.uvr5_pack.lib_v5.model_param_init import ModelParameters
|
||||
|
||||
from infer.lib.uvr5_pack.lib_v5.nets_new import CascadedNet
|
||||
from infer.lib.uvr5_pack.lib_v5 import nets_61968KB as Nets
|
||||
from infer.lib.uvr5_pack.lib_v5 import spec_utils
|
||||
from infer.lib.uvr5_pack.lib_v5.model_param_init import ModelParameters
|
||||
from infer.lib.uvr5_pack.lib_v5.nets_new import CascadedNet
|
||||
from infer.lib.uvr5_pack.utils import inference
|
||||
|
||||
|
||||
class AudioPre:
|
||||
|
@ -1,9 +1,10 @@
|
||||
import traceback
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import soundfile as sf
|
||||
import torch
|
||||
|
||||
from infer.lib.audio import load_audio
|
||||
from infer.lib.infer_pack.models import (
|
||||
SynthesizerTrnMs256NSFsid,
|
||||
SynthesizerTrnMs256NSFsid_nono,
|
||||
@ -12,7 +13,6 @@ from infer.lib.infer_pack.models import (
|
||||
)
|
||||
from infer.modules.vc.pipeline import Pipeline
|
||||
from infer.modules.vc.utils import *
|
||||
from infer.lib.audio import load_audio
|
||||
|
||||
|
||||
class VC:
|
||||
|
@ -1,13 +1,18 @@
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
from functools import lru_cache
|
||||
from time import time as ttime
|
||||
|
||||
import faiss
|
||||
import librosa
|
||||
import numpy as np
|
||||
import parselmouth
|
||||
import pyworld
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
import pyworld, os, traceback, faiss, librosa, torchcrepe
|
||||
import torchcrepe
|
||||
from scipy import signal
|
||||
from functools import lru_cache
|
||||
|
||||
now_dir = os.getcwd()
|
||||
sys.path.append(now_dir)
|
||||
|
@ -1,6 +1,8 @@
|
||||
# This code references https://huggingface.co/JosephusCheung/ASimilarityCalculatior/blob/main/qwerty.py
|
||||
# Fill in the path of the model to be queried and the root directory of the reference models, and this script will return the similarity between the model to be queried and all reference models.
|
||||
import sys, os
|
||||
import os
|
||||
import sys
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
@ -1,5 +1,5 @@
|
||||
from lib.infer_pack.models_onnx import SynthesizerTrnMsNSFsidM
|
||||
import torch
|
||||
from lib.infer_pack.models_onnx import SynthesizerTrnMsNSFsidM
|
||||
|
||||
if __name__ == "__main__":
|
||||
MoeVS = True # 模型是否为MoeVoiceStudio(原MoeSS)使用
|
||||
|
@ -2,34 +2,36 @@
|
||||
|
||||
对源特征进行检索
|
||||
"""
|
||||
import torch, pdb, os, parselmouth
|
||||
import os
|
||||
import pdb
|
||||
|
||||
import parselmouth
|
||||
import torch
|
||||
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
|
||||
# import torchcrepe
|
||||
from time import time as ttime
|
||||
|
||||
# import pyworld
|
||||
import librosa
|
||||
import numpy as np
|
||||
import scipy.signal as signal
|
||||
import soundfile as sf
|
||||
import torch.nn.functional as F
|
||||
from fairseq import checkpoint_utils
|
||||
|
||||
# from models import SynthesizerTrn256#hifigan_nonsf
|
||||
# from lib.infer_pack.models import SynthesizerTrn256NSF as SynthesizerTrn256#hifigan_nsf
|
||||
from lib.infer_pack.models import (
|
||||
SynthesizerTrnMs256NSFsid as SynthesizerTrn256,
|
||||
) # hifigan_nsf
|
||||
from scipy.io import wavfile
|
||||
|
||||
# from lib.infer_pack.models import SynthesizerTrnMs256NSFsid_sim as SynthesizerTrn256#hifigan_nsf
|
||||
# from models import SynthesizerTrn256NSFsim as SynthesizerTrn256#hifigan_nsf
|
||||
# from models import SynthesizerTrn256NSFsimFlow as SynthesizerTrn256#hifigan_nsf
|
||||
|
||||
|
||||
from scipy.io import wavfile
|
||||
from fairseq import checkpoint_utils
|
||||
|
||||
# import pyworld
|
||||
import librosa
|
||||
import torch.nn.functional as F
|
||||
import scipy.signal as signal
|
||||
|
||||
# import torchcrepe
|
||||
from time import time as ttime
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
model_path = r"E:\codes\py39\vits_vc_gpu_train\hubert_base.pt" #
|
||||
print("load model(s) from {}".format(model_path))
|
||||
|
@ -1,11 +1,14 @@
|
||||
"""
|
||||
格式:直接cid为自带的index位;aid放不下了,通过字典来查,反正就5w个
|
||||
"""
|
||||
import faiss, numpy as np, os
|
||||
from sklearn.cluster import MiniBatchKMeans
|
||||
import os
|
||||
import traceback
|
||||
from multiprocessing import cpu_count
|
||||
|
||||
import faiss
|
||||
import numpy as np
|
||||
from sklearn.cluster import MiniBatchKMeans
|
||||
|
||||
# ###########如果是原始特征要先写save
|
||||
n_cpu = 0
|
||||
if n_cpu == 0:
|
||||
|
@ -1,7 +1,10 @@
|
||||
"""
|
||||
格式:直接cid为自带的index位;aid放不下了,通过字典来查,反正就5w个
|
||||
"""
|
||||
import faiss, numpy as np, os
|
||||
import os
|
||||
|
||||
import faiss
|
||||
import numpy as np
|
||||
|
||||
# ###########如果是原始特征要先写save
|
||||
inp_root = r"E:\codes\py39\dataset\mi\2-co256"
|
||||
|
@ -1,4 +1,6 @@
|
||||
import torch, pdb
|
||||
import pdb
|
||||
|
||||
import torch
|
||||
|
||||
# a=torch.load(r"E:\codes\py39\vits_vc_gpu_train\logs\ft-mi-suc\G_1000.pth")["model"]#sim_nsf#
|
||||
# a=torch.load(r"E:\codes\py39\vits_vc_gpu_train\logs\ft-mi-freeze-vocoder-flow-enc_q\G_1000.pth")["model"]#sim_nsf#
|
||||
|
@ -1,4 +1,5 @@
|
||||
import soundfile
|
||||
|
||||
from ..lib.infer_pack.onnx_inference import OnnxRVC
|
||||
|
||||
hop_size = 512
|
||||
|
Loading…
Reference in New Issue
Block a user