mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2025-12-18 20:49:48 +01:00
chore(sync): merge dev into main (#1379)
* Optimize latency (#1259) * add attribute: configs/config.py Optimize latency: tools/rvc_for_realtime.py * new file: assets/Synthesizer_inputs.pth * fix: configs/config.py fix: tools/rvc_for_realtime.py * fix bug: infer/lib/infer_pack/models.py * new file: assets/hubert_inputs.pth new file: assets/rmvpe_inputs.pth modified: configs/config.py new features: infer/lib/rmvpe.py new features: tools/jit_export/__init__.py new features: tools/jit_export/get_hubert.py new features: tools/jit_export/get_rmvpe.py new features: tools/jit_export/get_synthesizer.py optimize: tools/rvc_for_realtime.py * optimize: tools/jit_export/get_synthesizer.py fix bug: tools/jit_export/__init__.py * Fixed a bug caused by using half on the CPU: infer/lib/rmvpe.py Fixed a bug caused by using half on the CPU: tools/jit_export/__init__.py Fixed CIRCULAR IMPORT: tools/jit_export/get_rmvpe.py Fixed CIRCULAR IMPORT: tools/jit_export/get_synthesizer.py Fixed a bug caused by using half on the CPU: tools/rvc_for_realtime.py * Remove useless code: infer/lib/rmvpe.py * Delete gui_v1 copy.py * Delete .vscode/launch.json * Delete jit_export_test.py * Delete tools/rvc_for_realtime copy.py * Delete configs/config.json * Delete .gitignore * Fix exceptions caused by switching inference devices: infer/lib/rmvpe.py Fix exceptions caused by switching inference devices: tools/jit_export/__init__.py Fix exceptions caused by switching inference devices: tools/rvc_for_realtime.py * restore * replace(you can undo this commit) * remove debug_print --------- Co-authored-by: Ftps <ftpsflandre@gmail.com> * Fixed some bugs when exporting ONNX model (#1254) * fix import (#1280) * fix import * lint * 🎨 同步 locale (#1242) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * Fix jit load and import issue (#1282) * fix jit model loading : infer/lib/rmvpe.py * modified: assets/hubert/.gitignore move file: assets/hubert_inputs.pth -> assets/hubert/hubert_inputs.pth modified: assets/rmvpe/.gitignore move file: assets/rmvpe_inputs.pth -> assets/rmvpe/rmvpe_inputs.pth fix import: gui_v1.py * feat(workflow): trigger on dev * feat(workflow): add close-pr on non-dev branch * Add input wav and delay time monitor for real-time gui (#1293) * feat(workflow): trigger on dev * feat(workflow): add close-pr on non-dev branch * 🎨 同步 locale (#1289) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * feat: edit PR template * add input wav and delay time monitor --------- Co-authored-by: 源文雨 <41315874+fumiama@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com> * Optimize latency using scripted jit (#1291) * feat(workflow): trigger on dev * feat(workflow): add close-pr on non-dev branch * 🎨 同步 locale (#1289) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * feat: edit PR template * Optimize-latency-using-scripted: configs/config.py Optimize-latency-using-scripted: infer/lib/infer_pack/attentions.py Optimize-latency-using-scripted: infer/lib/infer_pack/commons.py Optimize-latency-using-scripted: infer/lib/infer_pack/models.py Optimize-latency-using-scripted: infer/lib/infer_pack/modules.py Optimize-latency-using-scripted: infer/lib/jit/__init__.py Optimize-latency-using-scripted: infer/lib/jit/get_hubert.py Optimize-latency-using-scripted: infer/lib/jit/get_rmvpe.py Optimize-latency-using-scripted: infer/lib/jit/get_synthesizer.py Optimize-latency-using-scripted: infer/lib/rmvpe.py Optimize-latency-using-scripted: tools/rvc_for_realtime.py * modified: infer/lib/infer_pack/models.py * fix some bug: configs/config.py fix some bug: infer/lib/infer_pack/models.py fix some bug: infer/lib/rmvpe.py * Fixed abnormal reference of logger in multiprocessing: infer/modules/train/train.py --------- Co-authored-by: 源文雨 <41315874+fumiama@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * Format code (#1298) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * 🎨 同步 locale (#1299) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * feat: optimize actions * feat(workflow): add sync dev * feat: optimize actions * feat: optimize actions * feat: optimize actions * feat: optimize actions * feat: add jit options (#1303) Delete useless code: infer/lib/jit/get_synthesizer.py Optimized code: tools/rvc_for_realtime.py * Code refactor + re-design inference ui (#1304) * Code refacor + re-design inference ui * Fix tabname * i18n jp --------- Co-authored-by: Ftps <ftpsflandre@gmail.com> * feat: optimize actions * feat: optimize actions * Update README & en_US locale file (#1309) * critical: some bug fixes (#1322) * JIT acceleration switch does not support hot update * fix padding bug of rmvpe in torch-directml * fix padding bug of rmvpe in torch-directml * Fix STFT under torch_directml (#1330) * chore(format): run black on dev (#1318) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * chore(i18n): sync locale on dev (#1317) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * feat: allow for tta to be passed to uvr (#1361) * chore(format): run black on dev (#1373) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * Added script for automatically download all needed models at install (#1366) * Delete modules.py * Add files via upload * Add files via upload * Add files via upload * Add files via upload * chore(i18n): sync locale on dev (#1377) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * chore(format): run black on dev (#1376) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * Update IPEX library (#1362) * Update IPEX library * Update ipex index * chore(format): run black on dev (#1378) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> --------- Co-authored-by: Chengjia Jiang <46401978+ChasonJiang@users.noreply.github.com> Co-authored-by: Ftps <ftpsflandre@gmail.com> Co-authored-by: shizuku_nia <102004222+ShizukuNia@users.noreply.github.com> Co-authored-by: Ftps <63702646+Tps-F@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: 源文雨 <41315874+fumiama@users.noreply.github.com> Co-authored-by: yxlllc <33565655+yxlllc@users.noreply.github.com> Co-authored-by: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com> Co-authored-by: Blaise <133521603+blaise-tk@users.noreply.github.com> Co-authored-by: Rice Cake <gak141808@gmail.com> Co-authored-by: AWAS666 <33494149+AWAS666@users.noreply.github.com> Co-authored-by: Dmitry <nda2911@yandex.ru> Co-authored-by: Disty0 <47277141+Disty0@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
committed by
GitHub
GitHub
parent
fe166e7f3d
commit
e9dd11bddb
@@ -1,4 +1,5 @@
|
||||
import torch
|
||||
from infer.lib.rmvpe import STFT
|
||||
from torch.nn.functional import conv1d, conv2d
|
||||
from typing import Union, Optional
|
||||
from .utils import linspace, temperature_sigmoid, amp_to_db
|
||||
@@ -139,17 +140,26 @@ class TorchGate(torch.nn.Module):
|
||||
are set to 1, and the rest are set to 0.
|
||||
"""
|
||||
if xn is not None:
|
||||
XN = torch.stft(
|
||||
xn,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
return_complex=True,
|
||||
pad_mode="constant",
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(xn.device),
|
||||
)
|
||||
|
||||
if "privateuseone" in str(xn.device):
|
||||
if not hasattr(self, "stft"):
|
||||
self.stft = STFT(
|
||||
filter_length=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
window="hann",
|
||||
).to(xn.device)
|
||||
XN = self.stft.transform(xn)
|
||||
else:
|
||||
XN = torch.stft(
|
||||
xn,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
return_complex=True,
|
||||
pad_mode="constant",
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(xn.device),
|
||||
)
|
||||
XN_db = amp_to_db(XN).to(dtype=X_db.dtype)
|
||||
else:
|
||||
XN_db = X_db
|
||||
@@ -213,16 +223,26 @@ class TorchGate(torch.nn.Module):
|
||||
"""
|
||||
|
||||
# Compute short-time Fourier transform (STFT)
|
||||
X = torch.stft(
|
||||
x,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
return_complex=True,
|
||||
pad_mode="constant",
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(x.device),
|
||||
)
|
||||
if "privateuseone" in str(x.device):
|
||||
if not hasattr(self, "stft"):
|
||||
self.stft = STFT(
|
||||
filter_length=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
window="hann",
|
||||
).to(x.device)
|
||||
X, phase = self.stft.transform(x, return_phase=True)
|
||||
else:
|
||||
X = torch.stft(
|
||||
x,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
return_complex=True,
|
||||
pad_mode="constant",
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(x.device),
|
||||
)
|
||||
|
||||
# Compute signal mask based on stationary or nonstationary assumptions
|
||||
if self.nonstationary:
|
||||
@@ -231,7 +251,7 @@ class TorchGate(torch.nn.Module):
|
||||
sig_mask = self._stationary_mask(amp_to_db(X), xn)
|
||||
|
||||
# Propagate decrease in signal power
|
||||
sig_mask = self.prop_decrease * (sig_mask * 1.0 - 1.0) + 1.0
|
||||
sig_mask = self.prop_decrease * (sig_mask.float() - 1.0) + 1.0
|
||||
|
||||
# Smooth signal mask with 2D convolution
|
||||
if self.smoothing_filter is not None:
|
||||
@@ -245,13 +265,16 @@ class TorchGate(torch.nn.Module):
|
||||
Y = X * sig_mask.squeeze(1)
|
||||
|
||||
# Inverse STFT to obtain time-domain signal
|
||||
y = torch.istft(
|
||||
Y,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(Y.device),
|
||||
)
|
||||
if "privateuseone" in str(Y.device):
|
||||
y = self.stft.inverse(Y, phase)
|
||||
else:
|
||||
y = torch.istft(
|
||||
Y,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(Y.device),
|
||||
)
|
||||
|
||||
return y.to(dtype=x.dtype)
|
||||
|
||||
Reference in New Issue
Block a user