OPENGIT/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-05-06 20:01:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refactor wave-to-mel

Browse Source
This commit is contained in:
tarepan 2023-04-23 13:20:53 +00:00
parent a02ef401ad
commit 427ad79974
1 changed files with 4 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
train/mel_processing.py
View File

@ -100,61 +100,7 @@ def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
return spec
def mel_spectrogram_torch(
y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False
):
if torch.min(y) < -1.0:
print("min value is ", torch.min(y))
if torch.max(y) > 1.0:
print("max value is ", torch.max(y))
global mel_basis, hann_window
dtype_device = str(y.dtype) + "_" + str(y.device)
fmax_dtype_device = str(fmax) + "_" + dtype_device
wnsize_dtype_device = str(win_size) + "_" + dtype_device
if fmax_dtype_device not in mel_basis:
mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax)
mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
dtype=y.dtype, device=y.device
)
if wnsize_dtype_device not in hann_window:
hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(
dtype=y.dtype, device=y.device
)
y = torch.nn.functional.pad(
y.unsqueeze(1),
(int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)),
mode="reflect",
)
y = y.squeeze(1)
# spec = torch.stft(
# y,
# n_fft,
# hop_length=hop_size,
# win_length=win_size,
# window=hann_window[wnsize_dtype_device],
# center=center,
# pad_mode="reflect",
# normalized=False,
# onesided=True,
# )
spec = torch.stft(
y,
n_fft,
hop_length=hop_size,
win_length=win_size,
window=hann_window[wnsize_dtype_device],
center=center,
pad_mode="reflect",
normalized=False,
onesided=True,
return_complex=False,
)
spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
spec = spectral_normalize_torch(spec)
return spec
def mel_spectrogram_torch(y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False):
spec = spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center)
melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax)
return melspec