File size: 2,329 Bytes
85ce65e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import numpy as np
import torch
import torch.nn.functional as F
from librosa.filters import mel


class MelSpectrogram(torch.nn.Module):
    def __init__(
        self,
        n_mel_channels,
        sampling_rate,
        win_length,
        hop_length,
        n_fft=None,
        mel_fmin=0,
        mel_fmax=None,
        clamp = 1e-5
    ):
        super().__init__()
        n_fft = win_length if n_fft is None else n_fft
        self.hann_window = {}
        mel_basis = mel(
            sr=sampling_rate,
            n_fft=n_fft, 
            n_mels=n_mel_channels, 
            fmin=mel_fmin, 
            fmax=mel_fmax,
            htk=True)
        mel_basis = torch.from_numpy(mel_basis).float()
        self.register_buffer("mel_basis", mel_basis)
        self.n_fft = win_length if n_fft is None else n_fft
        self.hop_length = hop_length
        self.win_length = win_length
        self.sampling_rate = sampling_rate
        self.n_mel_channels = n_mel_channels
        self.clamp = clamp

    def forward(self, audio, keyshift=0, speed=1, center=True):
        factor = 2 ** (keyshift / 12)       
        n_fft_new = int(np.round(self.n_fft * factor))
        win_length_new = int(np.round(self.win_length * factor))
        hop_length_new = int(np.round(self.hop_length * speed))
        
        keyshift_key = str(keyshift)+'_'+str(audio.device)
        if keyshift_key not in self.hann_window:
            self.hann_window[keyshift_key] = torch.hann_window(win_length_new).to(audio.device)
            
        fft = torch.stft(
            audio,
            n_fft=n_fft_new,
            hop_length=hop_length_new,
            win_length=win_length_new,
            window=self.hann_window[keyshift_key],
            center=center,
            return_complex=True)
        magnitude = torch.sqrt(fft.real.pow(2) + fft.imag.pow(2))
        
        if keyshift != 0:
            size = self.n_fft // 2 + 1
            resize = magnitude.size(1)
            if resize < size:
                magnitude = F.pad(magnitude, (0, 0, 0, size-resize))
            magnitude = magnitude[:, :size, :] * self.win_length / win_length_new
            
        mel_output = torch.matmul(self.mel_basis, magnitude)
        log_mel_spec = torch.log(torch.clamp(mel_output, min=self.clamp))
        return log_mel_spec