File size: 2,364 Bytes
9a83644
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
import numpy as np
import torch
import torch.utils.data
from librosa.filters import mel as librosa_mel_fn
from scipy.io.wavfile import read

MAX_WAV_VALUE = 32768.0


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


def dynamic_range_compression(x, C=1, clip_val=1e-5):
    return np.log(np.clip(x, a_min=clip_val, a_max=None) * C)


def dynamic_range_decompression(x, C=1):
    return np.exp(x) / C


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


def dynamic_range_decompression_torch(x, C=1):
    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 mel_spectrogram(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  # pylint: disable=global-statement
    if f"{str(fmax)}_{str(y.device)}" not in mel_basis:
        mel = librosa_mel_fn(sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=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.view_as_real(
        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=True,
        )
    )

    spec = torch.sqrt(spec.pow(2).sum(-1) + (1e-9))

    spec = torch.matmul(mel_basis[str(fmax) + "_" + str(y.device)], spec)
    spec = spectral_normalize_torch(spec)

    return spec