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 mel module import and variable names

Browse Source
This commit is contained in:
tarepan 2023-04-23 13:40:17 +00:00
parent ec2ec9032e
commit 2e60c12044
1 changed files with 10 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
train/mel_processing.py
View File

@ -1,18 +1,8 @@
import math
import os
import random
import torch import torch
from torch import nn
import torch.nn.functional as F
import torch.utils.data import torch.utils.data
import numpy as np
import librosa
import librosa.util as librosa_util
from librosa.util import normalize, pad_center, tiny
from scipy.signal import get_window
from scipy.io.wavfile import read
from librosa.filters import mel as librosa_mel_fn from librosa.filters import mel as librosa_mel_fn
MAX_WAV_VALUE = 32768.0 MAX_WAV_VALUE = 32768.0
@ -35,13 +25,11 @@ def dynamic_range_decompression_torch(x, C=1):
def spectral_normalize_torch(magnitudes): def spectral_normalize_torch(magnitudes):
output = dynamic_range_compression_torch(magnitudes) return dynamic_range_compression_torch(magnitudes)
return output
def spectral_de_normalize_torch(magnitudes): def spectral_de_normalize_torch(magnitudes):
output = dynamic_range_decompression_torch(magnitudes) return dynamic_range_decompression_torch(magnitudes)
return output
# Reusable banks # Reusable banks
@ -116,12 +104,14 @@ def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
) )
# Mel-frequency Log-amplitude spectrogram :: (B, Freq=num_mels, Frame) # Mel-frequency Log-amplitude spectrogram :: (B, Freq=num_mels, Frame)
spec = torch.matmul(mel_basis[fmax_dtype_device], spec) melspec = torch.matmul(mel_basis[fmax_dtype_device], spec)
spec = spectral_normalize_torch(spec) melspec = spectral_normalize_torch(melspec)
return spec return melspec
def mel_spectrogram_torch(y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False): def mel_spectrogram_torch(
y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False
):
"""Convert waveform into Mel-frequency Log-amplitude spectrogram. """Convert waveform into Mel-frequency Log-amplitude spectrogram.
Args: Args:
@ -135,4 +125,4 @@ def mel_spectrogram_torch(y, n_fft, num_mels, sampling_rate, hop_size, win_size,
# Mel-frequency Log-amplitude spectrogram :: (B, Freq, Frame) -> (B, Freq=num_mels, Frame) # Mel-frequency Log-amplitude spectrogram :: (B, Freq, Frame) -> (B, Freq=num_mels, Frame)
melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax) melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax)
return melspec return melspec