mel_processing.py

import math
import os
from packaging import version
import random
import torch
from torch import nn
import torch.nn.functional as F
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

MAX_WAV_VALUE = 32768.0


def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
    """
    PARAMS
    ------
    C: compression factor
    """
    return torch.log(torch.clamp(x, min=clip_val) * C)


def dynamic_range_decompression_torch(x, C=1):
    """
    PARAMS
    ------
    C: compression factor used to compress
    """
    return torch.exp(x) / C


def spectral_normalize_torch(magnitudes):
    output = dynamic_range_compression_torch(magnitudes)
    return output


def spectral_de_normalize_torch(magnitudes):
    output = dynamic_range_decompression_torch(magnitudes)
    return output


mel_basis = {}
hann_window = {}


def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False):
    if torch.min(y) < -1.:
        print('min value is ', torch.min(y))
    if torch.max(y) > 1.:
        print('max value is ', torch.max(y))

    global hann_window
    dtype_device = str(y.dtype) + '_' + str(y.device)
    wnsize_dtype_device = str(win_size) + '_' + dtype_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)

    if version.parse(torch.__version__) >= version.parse("2"):
        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)
    else:
        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.sqrt(spec.pow(2).sum(-1) + 1e-6)
    return spec


def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
    global mel_basis
    dtype_device = str(spec.dtype) + '_' + str(spec.device)
    fmax_dtype_device = str(fmax) + '_' + 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=spec.dtype, device=spec.device)
    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):
    if torch.min(y) < -1.:
        print('min value is ', torch.min(y))
    if torch.max(y) > 1.:
        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)

    if version.parse(torch.__version__) >= version.parse("2"):
        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)
    else:
        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)
    '''
    #- reserve : from https://github.com/jaywalnut310/vits/issues/15#issuecomment-1084148441
    with autocast(enabled=False):
        y = y.float()
        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.sqrt(spec.pow(2).sum(-1) + 1e-6)

    spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
    spec = spectral_normalize_torch(spec)

    return spec