RVC/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-01-20 02:51:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(format): run black on dev (#1638)

Browse Source 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
2023-12-26 22:03:02 +09:00
committed by GitHub
parent 997a956f4f
commit 5449f84f06
4 changed files with 102 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
infer/lib/infer_pack/models.py
View File

@@ -795,9 +795,9 @@ class SynthesizerTrnMs256NSFsid(nn.Module):
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
nsff0 = nsff0[:, head: head + length]
z_p = z_p[:, :, head : head + length]
x_mask = x_mask[:, :, head : head + length]
nsff0 = nsff0[:, head : head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, nsff0, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@@ -957,9 +957,9 @@ class SynthesizerTrnMs768NSFsid(nn.Module):
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
nsff0 = nsff0[:, head: head + length]
z_p = z_p[:, :, head : head + length]
x_mask = x_mask[:, :, head : head + length]
nsff0 = nsff0[:, head : head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, nsff0, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@@ -1108,8 +1108,8 @@ class SynthesizerTrnMs256NSFsid_nono(nn.Module):
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
z_p = z_p[:, :, head : head + length]
x_mask = x_mask[:, :, head : head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@@ -1258,8 +1258,8 @@ class SynthesizerTrnMs768NSFsid_nono(nn.Module):
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
z_p = z_p[:, :, head : head + length]
x_mask = x_mask[:, :, head : head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)

10
infer/lib/train/mel_processing.py
View File

@@ -38,6 +38,7 @@ def spectral_de_normalize_torch(magnitudes):
mel_basis = {}
hann_window = {}
def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False):
"""Convert waveform into Linear-frequency Linear-amplitude spectrogram.
@@ -51,7 +52,7 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False)
Returns:
:: (B, Freq, Frame) - Linear-frequency Linear-amplitude spectrogram
"""
# Window - Cache if needed
global hann_window
dtype_device = str(y.dtype) + "_" + str(y.device)
@@ -60,7 +61,7 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False)
hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(
dtype=y.dtype, device=y.device
)
# Padding
y = torch.nn.functional.pad(
y.unsqueeze(1),
@@ -68,7 +69,7 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False)
mode="reflect",
)
y = y.squeeze(1)
# Complex Spectrogram :: (B, T) -> (B, Freq, Frame, RealComplex=2)
spec = torch.stft(
y,
@@ -82,11 +83,12 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False)
onesided=True,
return_complex=True,
)
# Linear-frequency Linear-amplitude spectrogram :: (B, Freq, Frame, RealComplex=2) -> (B, Freq, Frame)
spec = torch.sqrt(spec.real.pow(2) + spec.imag.pow(2) + 1e-6)
return spec
def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
# MelBasis - Cache if needed
global mel_basis