File size: 2,369 Bytes
85d3b29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
84
85
import torch
import torch.utils.data
from librosa.filters import mel as librosa_mel_fn


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):
    return dynamic_range_compression_torch(magnitudes)


def spectral_de_normalize_torch(magnitudes):
    return dynamic_range_decompression_torch(magnitudes)


mel_basis = {}
hann_window = {}


def spectrogram_torch(y, n_fft, hop_size, win_size, center=False):
    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)

    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=True,
    )

    spec = torch.sqrt(spec.real.pow(2) + spec.imag.pow(2) + 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(
            sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax
        )
        mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
            dtype=spec.dtype, device=spec.device
        )

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


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, hop_size, win_size, center)

    melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax)

    return melspec