diff --git a/voice_conversion/uvr5_pack/lib_v5/dataset.py b/voice_conversion/uvr5_pack/lib_v5/dataset.py deleted file mode 100644 index ba0e45b..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/dataset.py +++ /dev/null @@ -1,183 +0,0 @@ -import os -import random - -import numpy as np -import torch -import torch.utils.data -from tqdm import tqdm - -from uvr5_pack.lib_v5 import spec_utils - - -class VocalRemoverValidationSet(torch.utils.data.Dataset): - def __init__(self, patch_list): - self.patch_list = patch_list - - def __len__(self): - return len(self.patch_list) - - def __getitem__(self, idx): - path = self.patch_list[idx] - data = np.load(path) - - X, y = data["X"], data["y"] - - X_mag = np.abs(X) - y_mag = np.abs(y) - - return X_mag, y_mag - - -def make_pair(mix_dir, inst_dir): - input_exts = [".wav", ".m4a", ".mp3", ".mp4", ".flac"] - - X_list = sorted( - [ - os.path.join(mix_dir, fname) - for fname in os.listdir(mix_dir) - if os.path.splitext(fname)[1] in input_exts - ] - ) - y_list = sorted( - [ - os.path.join(inst_dir, fname) - for fname in os.listdir(inst_dir) - if os.path.splitext(fname)[1] in input_exts - ] - ) - - filelist = list(zip(X_list, y_list)) - - return filelist - - -def train_val_split(dataset_dir, split_mode, val_rate, val_filelist): - if split_mode == "random": - filelist = make_pair( - os.path.join(dataset_dir, "mixtures"), - os.path.join(dataset_dir, "instruments"), - ) - - random.shuffle(filelist) - - if len(val_filelist) == 0: - val_size = int(len(filelist) * val_rate) - train_filelist = filelist[:-val_size] - val_filelist = filelist[-val_size:] - else: - train_filelist = [ - pair for pair in filelist if list(pair) not in val_filelist - ] - elif split_mode == "subdirs": - if len(val_filelist) != 0: - raise ValueError( - "The `val_filelist` option is not available in `subdirs` mode" - ) - - train_filelist = make_pair( - os.path.join(dataset_dir, "training/mixtures"), - os.path.join(dataset_dir, "training/instruments"), - ) - - val_filelist = make_pair( - os.path.join(dataset_dir, "validation/mixtures"), - os.path.join(dataset_dir, "validation/instruments"), - ) - - return train_filelist, val_filelist - - -def augment(X, y, reduction_rate, reduction_mask, mixup_rate, mixup_alpha): - perm = np.random.permutation(len(X)) - for i, idx in enumerate(tqdm(perm)): - if np.random.uniform() < reduction_rate: - y[idx] = spec_utils.reduce_vocal_aggressively( - X[idx], y[idx], reduction_mask - ) - - if np.random.uniform() < 0.5: - # swap channel - X[idx] = X[idx, ::-1] - y[idx] = y[idx, ::-1] - if np.random.uniform() < 0.02: - # mono - X[idx] = X[idx].mean(axis=0, keepdims=True) - y[idx] = y[idx].mean(axis=0, keepdims=True) - if np.random.uniform() < 0.02: - # inst - X[idx] = y[idx] - - if np.random.uniform() < mixup_rate and i < len(perm) - 1: - lam = np.random.beta(mixup_alpha, mixup_alpha) - X[idx] = lam * X[idx] + (1 - lam) * X[perm[i + 1]] - y[idx] = lam * y[idx] + (1 - lam) * y[perm[i + 1]] - - return X, y - - -def make_padding(width, cropsize, offset): - left = offset - roi_size = cropsize - left * 2 - if roi_size == 0: - roi_size = cropsize - right = roi_size - (width % roi_size) + left - - return left, right, roi_size - - -def make_training_set(filelist, cropsize, patches, sr, hop_length, n_fft, offset): - len_dataset = patches * len(filelist) - - X_dataset = np.zeros((len_dataset, 2, n_fft // 2 + 1, cropsize), dtype=np.complex64) - y_dataset = np.zeros((len_dataset, 2, n_fft // 2 + 1, cropsize), dtype=np.complex64) - - for i, (X_path, y_path) in enumerate(tqdm(filelist)): - X, y = spec_utils.cache_or_load(X_path, y_path, sr, hop_length, n_fft) - coef = np.max([np.abs(X).max(), np.abs(y).max()]) - X, y = X / coef, y / coef - - l, r, roi_size = make_padding(X.shape[2], cropsize, offset) - X_pad = np.pad(X, ((0, 0), (0, 0), (l, r)), mode="constant") - y_pad = np.pad(y, ((0, 0), (0, 0), (l, r)), mode="constant") - - starts = np.random.randint(0, X_pad.shape[2] - cropsize, patches) - ends = starts + cropsize - for j in range(patches): - idx = i * patches + j - X_dataset[idx] = X_pad[:, :, starts[j] : ends[j]] - y_dataset[idx] = y_pad[:, :, starts[j] : ends[j]] - - return X_dataset, y_dataset - - -def make_validation_set(filelist, cropsize, sr, hop_length, n_fft, offset): - patch_list = [] - patch_dir = "cs{}_sr{}_hl{}_nf{}_of{}".format( - cropsize, sr, hop_length, n_fft, offset - ) - os.makedirs(patch_dir, exist_ok=True) - - for i, (X_path, y_path) in enumerate(tqdm(filelist)): - basename = os.path.splitext(os.path.basename(X_path))[0] - - X, y = spec_utils.cache_or_load(X_path, y_path, sr, hop_length, n_fft) - coef = np.max([np.abs(X).max(), np.abs(y).max()]) - X, y = X / coef, y / coef - - l, r, roi_size = make_padding(X.shape[2], cropsize, offset) - X_pad = np.pad(X, ((0, 0), (0, 0), (l, r)), mode="constant") - y_pad = np.pad(y, ((0, 0), (0, 0), (l, r)), mode="constant") - - len_dataset = int(np.ceil(X.shape[2] / roi_size)) - for j in range(len_dataset): - outpath = os.path.join(patch_dir, "{}_p{}.npz".format(basename, j)) - start = j * roi_size - if not os.path.exists(outpath): - np.savez( - outpath, - X=X_pad[:, :, start : start + cropsize], - y=y_pad[:, :, start : start + cropsize], - ) - patch_list.append(outpath) - - return VocalRemoverValidationSet(patch_list) diff --git a/voice_conversion/uvr5_pack/lib_v5/layers.py b/voice_conversion/uvr5_pack/lib_v5/layers.py deleted file mode 100644 index 9835dc0..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/layers.py +++ /dev/null @@ -1,118 +0,0 @@ -import torch -from torch import nn -import torch.nn.functional as F - -from uvr5_pack.lib_v5 import spec_utils - - -class Conv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(Conv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nout, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - bias=False, - ), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class SeperableConv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(SeperableConv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nin, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - groups=nin, - bias=False, - ), - nn.Conv2d(nin, nout, kernel_size=1, bias=False), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class Encoder(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU): - super(Encoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ) - - def __call__(self, x): - skip = self.conv1(x) - h = self.conv2(skip) - - return h, skip - - -class Decoder(nn.Module): - def __init__( - self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False - ): - super(Decoder, self).__init__() - self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def __call__(self, x, skip=None): - x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True) - if skip is not None: - skip = spec_utils.crop_center(skip, x) - x = torch.cat([x, skip], dim=1) - h = self.conv(x) - - if self.dropout is not None: - h = self.dropout(h) - - return h - - -class ASPPModule(nn.Module): - def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU): - super(ASPPModule, self).__init__() - self.conv1 = nn.Sequential( - nn.AdaptiveAvgPool2d((1, None)), - Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ), - ) - self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ) - self.conv3 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[0], dilations[0], activ=activ - ) - self.conv4 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[1], dilations[1], activ=activ - ) - self.conv5 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.bottleneck = nn.Sequential( - Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1) - ) - - def forward(self, x): - _, _, h, w = x.size() - feat1 = F.interpolate( - self.conv1(x), size=(h, w), mode="bilinear", align_corners=True - ) - feat2 = self.conv2(x) - feat3 = self.conv3(x) - feat4 = self.conv4(x) - feat5 = self.conv5(x) - out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1) - bottle = self.bottleneck(out) - return bottle diff --git a/voice_conversion/uvr5_pack/lib_v5/layers_123812KB .py b/voice_conversion/uvr5_pack/lib_v5/layers_123812KB .py deleted file mode 100644 index 9835dc0..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/layers_123812KB .py +++ /dev/null @@ -1,118 +0,0 @@ -import torch -from torch import nn -import torch.nn.functional as F - -from uvr5_pack.lib_v5 import spec_utils - - -class Conv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(Conv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nout, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - bias=False, - ), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class SeperableConv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(SeperableConv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nin, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - groups=nin, - bias=False, - ), - nn.Conv2d(nin, nout, kernel_size=1, bias=False), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class Encoder(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU): - super(Encoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ) - - def __call__(self, x): - skip = self.conv1(x) - h = self.conv2(skip) - - return h, skip - - -class Decoder(nn.Module): - def __init__( - self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False - ): - super(Decoder, self).__init__() - self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def __call__(self, x, skip=None): - x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True) - if skip is not None: - skip = spec_utils.crop_center(skip, x) - x = torch.cat([x, skip], dim=1) - h = self.conv(x) - - if self.dropout is not None: - h = self.dropout(h) - - return h - - -class ASPPModule(nn.Module): - def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU): - super(ASPPModule, self).__init__() - self.conv1 = nn.Sequential( - nn.AdaptiveAvgPool2d((1, None)), - Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ), - ) - self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ) - self.conv3 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[0], dilations[0], activ=activ - ) - self.conv4 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[1], dilations[1], activ=activ - ) - self.conv5 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.bottleneck = nn.Sequential( - Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1) - ) - - def forward(self, x): - _, _, h, w = x.size() - feat1 = F.interpolate( - self.conv1(x), size=(h, w), mode="bilinear", align_corners=True - ) - feat2 = self.conv2(x) - feat3 = self.conv3(x) - feat4 = self.conv4(x) - feat5 = self.conv5(x) - out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1) - bottle = self.bottleneck(out) - return bottle diff --git a/voice_conversion/uvr5_pack/lib_v5/layers_123821KB.py b/voice_conversion/uvr5_pack/lib_v5/layers_123821KB.py deleted file mode 100644 index 9835dc0..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/layers_123821KB.py +++ /dev/null @@ -1,118 +0,0 @@ -import torch -from torch import nn -import torch.nn.functional as F - -from uvr5_pack.lib_v5 import spec_utils - - -class Conv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(Conv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nout, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - bias=False, - ), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class SeperableConv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(SeperableConv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nin, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - groups=nin, - bias=False, - ), - nn.Conv2d(nin, nout, kernel_size=1, bias=False), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class Encoder(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU): - super(Encoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ) - - def __call__(self, x): - skip = self.conv1(x) - h = self.conv2(skip) - - return h, skip - - -class Decoder(nn.Module): - def __init__( - self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False - ): - super(Decoder, self).__init__() - self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def __call__(self, x, skip=None): - x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True) - if skip is not None: - skip = spec_utils.crop_center(skip, x) - x = torch.cat([x, skip], dim=1) - h = self.conv(x) - - if self.dropout is not None: - h = self.dropout(h) - - return h - - -class ASPPModule(nn.Module): - def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU): - super(ASPPModule, self).__init__() - self.conv1 = nn.Sequential( - nn.AdaptiveAvgPool2d((1, None)), - Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ), - ) - self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ) - self.conv3 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[0], dilations[0], activ=activ - ) - self.conv4 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[1], dilations[1], activ=activ - ) - self.conv5 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.bottleneck = nn.Sequential( - Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1) - ) - - def forward(self, x): - _, _, h, w = x.size() - feat1 = F.interpolate( - self.conv1(x), size=(h, w), mode="bilinear", align_corners=True - ) - feat2 = self.conv2(x) - feat3 = self.conv3(x) - feat4 = self.conv4(x) - feat5 = self.conv5(x) - out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1) - bottle = self.bottleneck(out) - return bottle diff --git a/voice_conversion/uvr5_pack/lib_v5/layers_33966KB.py b/voice_conversion/uvr5_pack/lib_v5/layers_33966KB.py deleted file mode 100644 index 78e5392..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/layers_33966KB.py +++ /dev/null @@ -1,126 +0,0 @@ -import torch -from torch import nn -import torch.nn.functional as F - -from uvr5_pack.lib_v5 import spec_utils - - -class Conv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(Conv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nout, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - bias=False, - ), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class SeperableConv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(SeperableConv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nin, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - groups=nin, - bias=False, - ), - nn.Conv2d(nin, nout, kernel_size=1, bias=False), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class Encoder(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU): - super(Encoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ) - - def __call__(self, x): - skip = self.conv1(x) - h = self.conv2(skip) - - return h, skip - - -class Decoder(nn.Module): - def __init__( - self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False - ): - super(Decoder, self).__init__() - self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def __call__(self, x, skip=None): - x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True) - if skip is not None: - skip = spec_utils.crop_center(skip, x) - x = torch.cat([x, skip], dim=1) - h = self.conv(x) - - if self.dropout is not None: - h = self.dropout(h) - - return h - - -class ASPPModule(nn.Module): - def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU): - super(ASPPModule, self).__init__() - self.conv1 = nn.Sequential( - nn.AdaptiveAvgPool2d((1, None)), - Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ), - ) - self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ) - self.conv3 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[0], dilations[0], activ=activ - ) - self.conv4 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[1], dilations[1], activ=activ - ) - self.conv5 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.conv6 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.conv7 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.bottleneck = nn.Sequential( - Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1) - ) - - def forward(self, x): - _, _, h, w = x.size() - feat1 = F.interpolate( - self.conv1(x), size=(h, w), mode="bilinear", align_corners=True - ) - feat2 = self.conv2(x) - feat3 = self.conv3(x) - feat4 = self.conv4(x) - feat5 = self.conv5(x) - feat6 = self.conv6(x) - feat7 = self.conv7(x) - out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1) - bottle = self.bottleneck(out) - return bottle diff --git a/voice_conversion/uvr5_pack/lib_v5/layers_537227KB.py b/voice_conversion/uvr5_pack/lib_v5/layers_537227KB.py deleted file mode 100644 index 78e5392..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/layers_537227KB.py +++ /dev/null @@ -1,126 +0,0 @@ -import torch -from torch import nn -import torch.nn.functional as F - -from uvr5_pack.lib_v5 import spec_utils - - -class Conv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(Conv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nout, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - bias=False, - ), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class SeperableConv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(SeperableConv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nin, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - groups=nin, - bias=False, - ), - nn.Conv2d(nin, nout, kernel_size=1, bias=False), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class Encoder(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU): - super(Encoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ) - - def __call__(self, x): - skip = self.conv1(x) - h = self.conv2(skip) - - return h, skip - - -class Decoder(nn.Module): - def __init__( - self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False - ): - super(Decoder, self).__init__() - self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def __call__(self, x, skip=None): - x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True) - if skip is not None: - skip = spec_utils.crop_center(skip, x) - x = torch.cat([x, skip], dim=1) - h = self.conv(x) - - if self.dropout is not None: - h = self.dropout(h) - - return h - - -class ASPPModule(nn.Module): - def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU): - super(ASPPModule, self).__init__() - self.conv1 = nn.Sequential( - nn.AdaptiveAvgPool2d((1, None)), - Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ), - ) - self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ) - self.conv3 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[0], dilations[0], activ=activ - ) - self.conv4 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[1], dilations[1], activ=activ - ) - self.conv5 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.conv6 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.conv7 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.bottleneck = nn.Sequential( - Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1) - ) - - def forward(self, x): - _, _, h, w = x.size() - feat1 = F.interpolate( - self.conv1(x), size=(h, w), mode="bilinear", align_corners=True - ) - feat2 = self.conv2(x) - feat3 = self.conv3(x) - feat4 = self.conv4(x) - feat5 = self.conv5(x) - feat6 = self.conv6(x) - feat7 = self.conv7(x) - out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1) - bottle = self.bottleneck(out) - return bottle diff --git a/voice_conversion/uvr5_pack/lib_v5/layers_537238KB.py b/voice_conversion/uvr5_pack/lib_v5/layers_537238KB.py deleted file mode 100644 index 78e5392..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/layers_537238KB.py +++ /dev/null @@ -1,126 +0,0 @@ -import torch -from torch import nn -import torch.nn.functional as F - -from uvr5_pack.lib_v5 import spec_utils - - -class Conv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(Conv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nout, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - bias=False, - ), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class SeperableConv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(SeperableConv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nin, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - groups=nin, - bias=False, - ), - nn.Conv2d(nin, nout, kernel_size=1, bias=False), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class Encoder(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU): - super(Encoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ) - - def __call__(self, x): - skip = self.conv1(x) - h = self.conv2(skip) - - return h, skip - - -class Decoder(nn.Module): - def __init__( - self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False - ): - super(Decoder, self).__init__() - self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def __call__(self, x, skip=None): - x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True) - if skip is not None: - skip = spec_utils.crop_center(skip, x) - x = torch.cat([x, skip], dim=1) - h = self.conv(x) - - if self.dropout is not None: - h = self.dropout(h) - - return h - - -class ASPPModule(nn.Module): - def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU): - super(ASPPModule, self).__init__() - self.conv1 = nn.Sequential( - nn.AdaptiveAvgPool2d((1, None)), - Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ), - ) - self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ) - self.conv3 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[0], dilations[0], activ=activ - ) - self.conv4 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[1], dilations[1], activ=activ - ) - self.conv5 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.conv6 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.conv7 = SeperableConv2DBNActiv( - nin, nin, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.bottleneck = nn.Sequential( - Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1) - ) - - def forward(self, x): - _, _, h, w = x.size() - feat1 = F.interpolate( - self.conv1(x), size=(h, w), mode="bilinear", align_corners=True - ) - feat2 = self.conv2(x) - feat3 = self.conv3(x) - feat4 = self.conv4(x) - feat5 = self.conv5(x) - feat6 = self.conv6(x) - feat7 = self.conv7(x) - out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1) - bottle = self.bottleneck(out) - return bottle diff --git a/voice_conversion/uvr5_pack/lib_v5/layers_new.py b/voice_conversion/uvr5_pack/lib_v5/layers_new.py deleted file mode 100644 index 2441f2d..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/layers_new.py +++ /dev/null @@ -1,125 +0,0 @@ -import torch -from torch import nn -import torch.nn.functional as F - -from uvr5_pack.lib_v5 import spec_utils - - -class Conv2DBNActiv(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU): - super(Conv2DBNActiv, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d( - nin, - nout, - kernel_size=ksize, - stride=stride, - padding=pad, - dilation=dilation, - bias=False, - ), - nn.BatchNorm2d(nout), - activ(), - ) - - def __call__(self, x): - return self.conv(x) - - -class Encoder(nn.Module): - def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU): - super(Encoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, stride, pad, activ=activ) - self.conv2 = Conv2DBNActiv(nout, nout, ksize, 1, pad, activ=activ) - - def __call__(self, x): - h = self.conv1(x) - h = self.conv2(h) - - return h - - -class Decoder(nn.Module): - def __init__( - self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False - ): - super(Decoder, self).__init__() - self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ) - # self.conv2 = Conv2DBNActiv(nout, nout, ksize, 1, pad, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def __call__(self, x, skip=None): - x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True) - - if skip is not None: - skip = spec_utils.crop_center(skip, x) - x = torch.cat([x, skip], dim=1) - - h = self.conv1(x) - # h = self.conv2(h) - - if self.dropout is not None: - h = self.dropout(h) - - return h - - -class ASPPModule(nn.Module): - def __init__(self, nin, nout, dilations=(4, 8, 12), activ=nn.ReLU, dropout=False): - super(ASPPModule, self).__init__() - self.conv1 = nn.Sequential( - nn.AdaptiveAvgPool2d((1, None)), - Conv2DBNActiv(nin, nout, 1, 1, 0, activ=activ), - ) - self.conv2 = Conv2DBNActiv(nin, nout, 1, 1, 0, activ=activ) - self.conv3 = Conv2DBNActiv( - nin, nout, 3, 1, dilations[0], dilations[0], activ=activ - ) - self.conv4 = Conv2DBNActiv( - nin, nout, 3, 1, dilations[1], dilations[1], activ=activ - ) - self.conv5 = Conv2DBNActiv( - nin, nout, 3, 1, dilations[2], dilations[2], activ=activ - ) - self.bottleneck = Conv2DBNActiv(nout * 5, nout, 1, 1, 0, activ=activ) - self.dropout = nn.Dropout2d(0.1) if dropout else None - - def forward(self, x): - _, _, h, w = x.size() - feat1 = F.interpolate( - self.conv1(x), size=(h, w), mode="bilinear", align_corners=True - ) - feat2 = self.conv2(x) - feat3 = self.conv3(x) - feat4 = self.conv4(x) - feat5 = self.conv5(x) - out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1) - out = self.bottleneck(out) - - if self.dropout is not None: - out = self.dropout(out) - - return out - - -class LSTMModule(nn.Module): - def __init__(self, nin_conv, nin_lstm, nout_lstm): - super(LSTMModule, self).__init__() - self.conv = Conv2DBNActiv(nin_conv, 1, 1, 1, 0) - self.lstm = nn.LSTM( - input_size=nin_lstm, hidden_size=nout_lstm // 2, bidirectional=True - ) - self.dense = nn.Sequential( - nn.Linear(nout_lstm, nin_lstm), nn.BatchNorm1d(nin_lstm), nn.ReLU() - ) - - def forward(self, x): - N, _, nbins, nframes = x.size() - h = self.conv(x)[:, 0] # N, nbins, nframes - h = h.permute(2, 0, 1) # nframes, N, nbins - h, _ = self.lstm(h) - h = self.dense(h.reshape(-1, h.size()[-1])) # nframes * N, nbins - h = h.reshape(nframes, N, 1, nbins) - h = h.permute(1, 2, 3, 0) - - return h diff --git a/voice_conversion/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json b/voice_conversion/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json deleted file mode 100644 index 72cb449..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json +++ /dev/null @@ -1,19 +0,0 @@ -{ - "bins": 1024, - "unstable_bins": 0, - "reduction_bins": 0, - "band": { - "1": { - "sr": 16000, - "hl": 512, - "n_fft": 2048, - "crop_start": 0, - "crop_stop": 1024, - "hpf_start": -1, - "res_type": "sinc_best" - } - }, - "sr": 16000, - "pre_filter_start": 1023, - "pre_filter_stop": 1024 -} \ No newline at end of file diff --git a/voice_conversion/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json b/voice_conversion/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json deleted file mode 100644 index 3c00ecf..0000000 --- a/voice_conversion/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json +++ /dev/null @@ -1,19 +0,0 @@ -{ - "bins": 1024, - "unstable_bins": 0, - "reduction_bins": 0, - "band": { - "1": { - "sr": 32000, - "hl": 512, - "n_fft": 2048, - "crop_start": 0, - "crop_stop": 1024, - "hpf_start": -1, - "res_type": "kaiser_fast" - } - }, - "sr": 32000, - "pre_filter_start": 1000, - "pre_filter_stop": 1021 -} \ No newline at end of file