bacow/GPT-SoVITS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Introduce Docker and Windows CI Workflow, Pre-commit Formatting, and Language Resource Auto-Download (#2351)

Browse Source 
* Docker Auto-Build Workflow

* Rename

* Update

* Fix Bugs

* Disable Progress Bar When workflows triggered

* Fix Wget

* Fix Bugs

* Fix Bugs

* Update Wget

* Update Workflows

* Accelerate Docker Image Building

* Fix Install.sh

* Add Skip-Check For Action Runner

* Fix Dockerfile

* .

* .

* .

* .

* Delete File in Runner

* Add Sort

* Delete More Files

* Delete More

* .

* .

* .

* Add Pre-Commit Hook
Update Docker

* Add Code Spell Check

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* Fix Bugs

* .

* Disable Progress Bar and Logs while using GitHub Actions

* .

* .

* Fix Bugs

* update conda

* fix bugs

* Fix Bugs

* fix bugs

* .

* .

* Quiet Installation

* fix bugs

* .

* fix bug

* .

* Fix pre-commit.ci and Docker

* fix bugs

* .

* Update Docker & Pre-Commit

* fix  bugs

* Update Req

* Update Req

* Update OpenCC

* update precommit

* .

* Update .pre-commit-config.yaml

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update Docs and fix bugs

* Fix \

* Fix MacOS

* .

* test

* .

* Add Tag Alias

* .

* fix bugs

* fix bugs

* make image smaller

* update pre-commit config

* .

* .

* fix bugs

* use miniconda

* Fix Wrong Path

* .

* debug

* debug

* revert

* Fix Bugs

* Update Docs, Add Dict Auto Download in install.sh

* update docker_build

* Update Docs for Install.sh

* update docker docs about architecture

* Add Xcode-Commandline-Tool Installation

* Update Docs

1. Add Missing VC17
2. Modufied the Order of FFmpeg Installation and Requirements Installation
3. Remove Duplicate FFmpeg

* Fix Wrong Cuda Version

* Update TESTED ENV

* Add PYTHONNOUSERSITE(-s)

* Fix Wrapper

* Update install.sh For Robustness

* Ignore .git

* Preload CUDNN For Ctranslate2

* Remove Gradio Warnings

* Update Colab

* Fix OpenCC Problems

* Update Win DLL Strategy

* Fix Onnxruntime-gpu NVRTC Error

* Fix Path Problems

* Add Windows Packages Workflow

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* .

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* Fix Path

* Fix Path

* Enable Logging

* Set 7-Zip compression level to maximum (-mx=9)

* Use Multithread in ONNX Session

* Fix Tag Bugs

* Add Time

* Add Time

* Add Time

* Compress More

* Copy DLL to Solve VC Runtime DLL Missing Issues

* Expose FFmpeg Errors, Copy Only Part of Visual C++ Runtime

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* WIP

* WIP

* WIP

* Update build_windows_packages.ps1

* Update install.sh

* Update build_windows_packages.ps1

* Update docker-publish.yaml

* Update install.sh

* Update Dockerfile

* Update docker_build.sh

* Update miniconda_install.sh

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update Colab-WebUI.ipynb

* Update Colab-Inference.ipynb

* Update docker-compose.yaml

* 更新 build_windows_packages.ps1

* Update install.sh

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
XXXXRT666
2025-05-26 05:45:14 +03:00
committed by GitHub
parent 13055fa569
commit d5e479dad6
58 changed files with 2096 additions and 987 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
tools/uvr5/lib/lib_v5/dataset.py
View File

@@ -32,18 +32,10 @@ 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
]
[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
]
[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))
@@ -65,14 +57,10 @@ def train_val_split(dataset_dir, split_mode, val_rate, val_filelist):
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
]
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"
)
raise ValueError("The `val_filelist` option is not available in `subdirs` mode")
train_filelist = make_pair(
os.path.join(dataset_dir, "training/mixtures"),
@@ -91,9 +79,7 @@ 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
)
y[idx] = spec_utils.reduce_vocal_aggressively(X[idx], y[idx], reduction_mask)
if np.random.uniform() < 0.5:
# swap channel
@@ -152,9 +138,7 @@ def make_training_set(filelist, cropsize, patches, sr, hop_length, n_fft, offset
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
)
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)):

24
tools/uvr5/lib/lib_v5/layers.py
View File

@@ -63,9 +63,7 @@ class Encoder(nn.Module):
class Decoder(nn.Module):
def __init__(
self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
):
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
@@ -91,24 +89,14 @@ class ASPPModule(nn.Module):
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)
)
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
)
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)

24
tools/uvr5/lib/lib_v5/layers_123812KB.py
View File

@@ -63,9 +63,7 @@ class Encoder(nn.Module):
class Decoder(nn.Module):
def __init__(
self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
):
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
@@ -91,24 +89,14 @@ class ASPPModule(nn.Module):
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)
)
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
)
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)

24
tools/uvr5/lib/lib_v5/layers_123821KB.py
View File

@@ -63,9 +63,7 @@ class Encoder(nn.Module):
class Decoder(nn.Module):
def __init__(
self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
):
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
@@ -91,24 +89,14 @@ class ASPPModule(nn.Module):
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)
)
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
)
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)

32
tools/uvr5/lib/lib_v5/layers_33966KB.py
View File

@@ -63,9 +63,7 @@ class Encoder(nn.Module):
class Decoder(nn.Module):
def __init__(
self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
):
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
@@ -91,30 +89,16 @@ class ASPPModule(nn.Module):
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)
)
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
)
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)

32
tools/uvr5/lib/lib_v5/layers_537227KB.py
View File

@@ -63,9 +63,7 @@ class Encoder(nn.Module):
class Decoder(nn.Module):
def __init__(
self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
):
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
@@ -91,30 +89,16 @@ class ASPPModule(nn.Module):
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)
)
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
)
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)

32
tools/uvr5/lib/lib_v5/layers_537238KB.py
View File

@@ -63,9 +63,7 @@ class Encoder(nn.Module):
class Decoder(nn.Module):
def __init__(
self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
):
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
@@ -91,30 +89,16 @@ class ASPPModule(nn.Module):
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)
)
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
)
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)

28
tools/uvr5/lib/lib_v5/layers_new.py
View File

@@ -40,9 +40,7 @@ class Encoder(nn.Module):
class Decoder(nn.Module):
def __init__(
self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
):
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)
@@ -72,23 +70,15 @@ class ASPPModule(nn.Module):
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.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
)
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)
@@ -106,12 +96,8 @@ 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()
)
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()

7
tools/uvr5/lib/lib_v5/model_param_init.py
View File

@@ -1,5 +1,4 @@
import json
import os
import pathlib
default_param = {}
@@ -48,9 +47,7 @@ class ModelParameters(object):
import zipfile
with zipfile.ZipFile(config_path, "r") as zip:
self.param = json.loads(
zip.read("param.json"), object_pairs_hook=int_keys
)
self.param = json.loads(zip.read("param.json"), object_pairs_hook=int_keys)
elif ".json" == pathlib.Path(config_path).suffix:
with open(config_path, "r") as f:
self.param = json.loads(f.read(), object_pairs_hook=int_keys)
@@ -65,5 +62,5 @@ class ModelParameters(object):
"stereo_n",
"reverse",
]:
if not k in self.param:
if k not in self.param:
self.param[k] = False

2
tools/uvr5/lib/lib_v5/nets.py
View File

@@ -3,8 +3,6 @@ import torch
import torch.nn.functional as F
from torch import nn
from . import spec_utils
class BaseASPPNet(nn.Module):
def __init__(self, nin, ch, dilations=(4, 8, 16)):

1
tools/uvr5/lib/lib_v5/nets_537227KB.py
View File

@@ -1,4 +1,3 @@
import numpy as np
import torch
import torch.nn.functional as F
from torch import nn

1
tools/uvr5/lib/lib_v5/nets_537238KB.py
View File

@@ -1,4 +1,3 @@
import numpy as np
import torch
import torch.nn.functional as F
from torch import nn

16
tools/uvr5/lib/lib_v5/nets_new.py
View File

@@ -6,9 +6,7 @@ from . import layers_new
class BaseNet(nn.Module):
def __init__(
self, nin, nout, nin_lstm, nout_lstm, dilations=((4, 2), (8, 4), (12, 6))
):
def __init__(self, nin, nout, nin_lstm, nout_lstm, dilations=((4, 2), (8, 4), (12, 6))):
super(BaseNet, self).__init__()
self.enc1 = layers_new.Conv2DBNActiv(nin, nout, 3, 1, 1)
self.enc2 = layers_new.Encoder(nout, nout * 2, 3, 2, 1)
@@ -56,21 +54,15 @@ class CascadedNet(nn.Module):
layers_new.Conv2DBNActiv(nout // 2, nout // 4, 1, 1, 0),
)
self.stg1_high_band_net = BaseNet(
2, nout // 4, self.nin_lstm // 2, nout_lstm // 2
)
self.stg1_high_band_net = BaseNet(2, nout // 4, self.nin_lstm // 2, nout_lstm // 2)
self.stg2_low_band_net = nn.Sequential(
BaseNet(nout // 4 + 2, nout, self.nin_lstm // 2, nout_lstm),
layers_new.Conv2DBNActiv(nout, nout // 2, 1, 1, 0),
)
self.stg2_high_band_net = BaseNet(
nout // 4 + 2, nout // 2, self.nin_lstm // 2, nout_lstm // 2
)
self.stg2_high_band_net = BaseNet(nout // 4 + 2, nout // 2, self.nin_lstm // 2, nout_lstm // 2)
self.stg3_full_band_net = BaseNet(
3 * nout // 4 + 2, nout, self.nin_lstm, nout_lstm
)
self.stg3_full_band_net = BaseNet(3 * nout // 4 + 2, nout, self.nin_lstm, nout_lstm)
self.out = nn.Conv2d(nout, 2, 1, bias=False)
self.aux_out = nn.Conv2d(3 * nout // 4, 2, 1, bias=False)

119
tools/uvr5/lib/lib_v5/spec_utils.py
View File

@@ -27,9 +27,7 @@ def crop_center(h1, h2):
return h1
def wave_to_spectrogram(
wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
):
def wave_to_spectrogram(wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False):
if reverse:
wave_left = np.flip(np.asfortranarray(wave[0]))
wave_right = np.flip(np.asfortranarray(wave[1]))
@@ -43,7 +41,7 @@ def wave_to_spectrogram(
wave_left = np.asfortranarray(wave[0])
wave_right = np.asfortranarray(wave[1])
spec_left = librosa.stft(wave_left, n_fft=n_fft, hop_length=hop_length)
spec_left = librosa.stft(wave_left, n_fft=n_fft, hop_length=hop_length)
spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
spec = np.asfortranarray([spec_left, spec_right])
@@ -51,9 +49,7 @@ def wave_to_spectrogram(
return spec
def wave_to_spectrogram_mt(
wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
):
def wave_to_spectrogram_mt(wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False):
import threading
if reverse:
@@ -103,21 +99,13 @@ def combine_spectrograms(specs, mp):
raise ValueError("Too much bins")
# lowpass fiter
if (
mp.param["pre_filter_start"] > 0
): # and mp.param['band'][bands_n]['res_type'] in ['scipy', 'polyphase']:
if mp.param["pre_filter_start"] > 0: # and mp.param['band'][bands_n]['res_type'] in ['scipy', 'polyphase']:
if bands_n == 1:
spec_c = fft_lp_filter(
spec_c, mp.param["pre_filter_start"], mp.param["pre_filter_stop"]
)
spec_c = fft_lp_filter(spec_c, mp.param["pre_filter_start"], mp.param["pre_filter_stop"])
else:
gp = 1
for b in range(
mp.param["pre_filter_start"] + 1, mp.param["pre_filter_stop"]
):
g = math.pow(
10, -(b - mp.param["pre_filter_start"]) * (3.5 - gp) / 20.0
)
for b in range(mp.param["pre_filter_start"] + 1, mp.param["pre_filter_stop"]):
g = math.pow(10, -(b - mp.param["pre_filter_start"]) * (3.5 - gp) / 20.0)
gp = g
spec_c[:, b, :] *= g
@@ -189,9 +177,7 @@ def mask_silence(mag, ref, thres=0.2, min_range=64, fade_size=32):
else:
e += fade_size
mag[:, :, s + fade_size : e - fade_size] += ref[
:, :, s + fade_size : e - fade_size
]
mag[:, :, s + fade_size : e - fade_size] += ref[:, :, s + fade_size : e - fade_size]
old_e = e
return mag
@@ -207,9 +193,7 @@ def cache_or_load(mix_path, inst_path, mp):
mix_basename = os.path.splitext(os.path.basename(mix_path))[0]
inst_basename = os.path.splitext(os.path.basename(inst_path))[0]
cache_dir = "mph{}".format(
hashlib.sha1(json.dumps(mp.param, sort_keys=True).encode("utf-8")).hexdigest()
)
cache_dir = "mph{}".format(hashlib.sha1(json.dumps(mp.param, sort_keys=True).encode("utf-8")).hexdigest())
mix_cache_dir = os.path.join("cache", cache_dir)
inst_cache_dir = os.path.join("cache", cache_dir)
@@ -230,31 +214,27 @@ def cache_or_load(mix_path, inst_path, mp):
if d == len(mp.param["band"]): # high-end band
X_wave[d], _ = librosa.load(
mix_path,
sr = bp["sr"],
mono = False,
dtype = np.float32,
res_type = bp["res_type"]
mix_path, sr=bp["sr"], mono=False, dtype=np.float32, res_type=bp["res_type"]
)
y_wave[d], _ = librosa.load(
inst_path,
sr = bp["sr"],
mono = False,
dtype = np.float32,
res_type = bp["res_type"],
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
else: # lower bands
X_wave[d] = librosa.resample(
X_wave[d + 1],
orig_sr = mp.param["band"][d + 1]["sr"],
target_sr = bp["sr"],
res_type = bp["res_type"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
y_wave[d] = librosa.resample(
y_wave[d + 1],
orig_sr = mp.param["band"][d + 1]["sr"],
target_sr = bp["sr"],
res_type = bp["res_type"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
X_wave[d], y_wave[d] = align_wave_head_and_tail(X_wave[d], y_wave[d])
@@ -302,9 +282,7 @@ def spectrogram_to_wave(spec, hop_length, mid_side, mid_side_b2, reverse):
if reverse:
return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
elif mid_side:
return np.asfortranarray(
[np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
)
return np.asfortranarray([np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)])
elif mid_side_b2:
return np.asfortranarray(
[
@@ -326,9 +304,7 @@ def spectrogram_to_wave_mt(spec, hop_length, mid_side, reverse, mid_side_b2):
global wave_left
wave_left = librosa.istft(**kwargs)
thread = threading.Thread(
target=run_thread, kwargs={"stft_matrix": spec_left, "hop_length": hop_length}
)
thread = threading.Thread(target=run_thread, kwargs={"stft_matrix": spec_left, "hop_length": hop_length})
thread.start()
wave_right = librosa.istft(spec_right, hop_length=hop_length)
thread.join()
@@ -336,9 +312,7 @@ def spectrogram_to_wave_mt(spec, hop_length, mid_side, reverse, mid_side_b2):
if reverse:
return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
elif mid_side:
return np.asfortranarray(
[np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
)
return np.asfortranarray([np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)])
elif mid_side_b2:
return np.asfortranarray(
[
@@ -357,21 +331,15 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
for d in range(1, bands_n + 1):
bp = mp.param["band"][d]
spec_s = np.ndarray(
shape=(2, bp["n_fft"] // 2 + 1, spec_m.shape[2]), dtype=complex
)
spec_s = np.ndarray(shape=(2, bp["n_fft"] // 2 + 1, spec_m.shape[2]), dtype=complex)
h = bp["crop_stop"] - bp["crop_start"]
spec_s[:, bp["crop_start"] : bp["crop_stop"], :] = spec_m[
:, offset : offset + h, :
]
spec_s[:, bp["crop_start"] : bp["crop_stop"], :] = spec_m[:, offset : offset + h, :]
offset += h
if d == bands_n: # higher
if extra_bins_h: # if --high_end_process bypass
max_bin = bp["n_fft"] // 2
spec_s[:, max_bin - extra_bins_h : max_bin, :] = extra_bins[
:, :extra_bins_h, :
]
spec_s[:, max_bin - extra_bins_h : max_bin, :] = extra_bins[:, :extra_bins_h, :]
if bp["hpf_start"] > 0:
spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
if bands_n == 1:
@@ -405,9 +373,9 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
mp.param["mid_side_b2"],
mp.param["reverse"],
),
orig_sr = bp["sr"],
target_sr = sr,
res_type = "sinc_fastest",
orig_sr=bp["sr"],
target_sr=sr,
res_type="sinc_fastest",
)
else: # mid
spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
@@ -456,10 +424,7 @@ def mirroring(a, spec_m, input_high_end, mp):
np.abs(
spec_m[
:,
mp.param["pre_filter_start"]
- 10
- input_high_end.shape[1] : mp.param["pre_filter_start"]
- 10,
mp.param["pre_filter_start"] - 10 - input_high_end.shape[1] : mp.param["pre_filter_start"] - 10,
:,
]
),
@@ -467,19 +432,14 @@ def mirroring(a, spec_m, input_high_end, mp):
)
mirror = mirror * np.exp(1.0j * np.angle(input_high_end))
return np.where(
np.abs(input_high_end) <= np.abs(mirror), input_high_end, mirror
)
return np.where(np.abs(input_high_end) <= np.abs(mirror), input_high_end, mirror)
if "mirroring2" == a:
mirror = np.flip(
np.abs(
spec_m[
:,
mp.param["pre_filter_start"]
- 10
- input_high_end.shape[1] : mp.param["pre_filter_start"]
- 10,
mp.param["pre_filter_start"] - 10 - input_high_end.shape[1] : mp.param["pre_filter_start"] - 10,
:,
]
),
@@ -528,7 +488,6 @@ def istft(spec, hl):
if __name__ == "__main__":
import argparse
import sys
import time
import cv2
@@ -573,10 +532,10 @@ if __name__ == "__main__":
if d == len(mp.param["band"]): # high-end band
wave[d], _ = librosa.load(
args.input[i],
sr = bp["sr"],
mono = False,
dtype = np.float32,
res_type = bp["res_type"],
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
if len(wave[d].shape) == 1: # mono to stereo
@@ -584,9 +543,9 @@ if __name__ == "__main__":
else: # lower bands
wave[d] = librosa.resample(
wave[d + 1],
orig_sr = mp.param["band"][d + 1]["sr"],
target_sr = bp["sr"],
res_type = bp["res_type"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
spec[d] = wave_to_spectrogram(

16
tools/uvr5/lib/utils.py
View File

@@ -27,9 +27,7 @@ def inference(X_spec, device, model, aggressiveness, data):
data : dic configs
"""
def _execute(
X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half=True
):
def _execute(X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half=True):
model.eval()
with torch.no_grad():
preds = []
@@ -39,9 +37,7 @@ def inference(X_spec, device, model, aggressiveness, data):
total_iterations = sum(iterations)
for i in tqdm(range(n_window)):
start = i * roi_size
X_mag_window = X_mag_pad[
None, :, :, start : start + data["window_size"]
]
X_mag_window = X_mag_pad[None, :, :, start : start + data["window_size"]]
X_mag_window = torch.from_numpy(X_mag_window)
if is_half:
X_mag_window = X_mag_window.half()
@@ -76,9 +72,7 @@ def inference(X_spec, device, model, aggressiveness, data):
is_half = True
else:
is_half = False
pred = _execute(
X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half
)
pred = _execute(X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half)
pred = pred[:, :, :n_frame]
if data["tta"]:
@@ -88,9 +82,7 @@ def inference(X_spec, device, model, aggressiveness, data):
X_mag_pad = np.pad(X_mag_pre, ((0, 0), (0, 0), (pad_l, pad_r)), mode="constant")
pred_tta = _execute(
X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half
)
pred_tta = _execute(X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half)
pred_tta = pred_tta[:, :, roi_size // 2 :]
pred_tta = pred_tta[:, :, :n_frame]

18
tools/uvr5/webui.py
View File

@@ -1,26 +1,22 @@
import logging
import os
import traceback
import gradio as gr
import logging
from tools.i18n.i18n import I18nAuto
from tools.my_utils import clean_path
i18n = I18nAuto()
logger = logging.getLogger(__name__)
import sys
import ffmpeg
import torch
import sys
from bsroformer import Roformer_Loader
from mdxnet import MDXNetDereverb
from vr import AudioPre, AudioPreDeEcho
from bsroformer import Roformer_Loader
try:
import gradio.analytics as analytics
analytics.version_check = lambda: None
except:
...
weight_uvr5_root = "tools/uvr5/uvr5_weights"
uvr5_names = []
@@ -129,7 +125,7 @@ def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins, agg, format
yield "\n".join(infos)
with gr.Blocks(title="UVR5 WebUI") as app:
with gr.Blocks(title="UVR5 WebUI", analytics_enabled=False) as app:
gr.Markdown(
value=i18n("本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.")
+ "<br>"