utils/audio_utils.py

import torch
import torch.utils.data
from scipy.io.wavfile import read
from librosa.filters import mel as librosa_mel_fn

MAX_WAV_VALUE = 32768.0


def load_wav(full_path):
    sampling_rate, data = read(full_path)
    return data, sampling_rate

def _dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
    return torch.log(torch.clamp(x, min=clip_val) * C)


def _spectral_normalize_torch(magnitudes):
    output = _dynamic_range_compression_torch(magnitudes)
    return output

mel_basis = {}
hann_window = {}

def mel_spectrogram(
    y, 
    n_fft, 
    num_mels, 
    sampling_rate, 
    hop_size, 
    win_size, 
    fmin, 
    fmax, 
    center=False,
    output_energy=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
    if fmax not in mel_basis:
        mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax)
        mel_basis[str(fmax)+'_'+str(y.device)] = torch.from_numpy(mel).float().to(y.device)
        hann_window[str(y.device)] = torch.hann_window(win_size).to(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[str(y.device)],
                      center=center, pad_mode='reflect', normalized=False, onesided=True, return_complex=False)
    spec = torch.sqrt(spec.pow(2).sum(-1)+(1e-9))
    mel_spec = torch.matmul(mel_basis[str(fmax)+'_'+str(y.device)], spec)
    mel_spec = _spectral_normalize_torch(mel_spec)
    if output_energy:
        energy = torch.norm(spec, dim=1)
        return mel_spec, energy
    else:
        return mel_spec