mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
94 lines
3.2 KiB
Python
94 lines
3.2 KiB
Python
import torch
|
|
import torch.utils.data
|
|
import numpy as np
|
|
from librosa.filters import mel as librosa_mel_fn
|
|
|
|
|
|
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.:
|
|
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(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.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)
|
|
|
|
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
|
|
|
|
|
|
def power_spectrogram(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
|
|
if fmax 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.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)
|
|
|
|
spec = torch.sqrt(spec.pow(2).sum(-1)+(1e-9))
|
|
spec = spectral_normalize_torch(spec)
|
|
|
|
return spec
|
|
|
|
|
|
def mel_from_power_spectrogram(spec, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False):
|
|
global mel_basis, hann_window
|
|
spec = spectral_de_normalize_torch(spec)
|
|
spec = torch.matmul(mel_basis[str(fmax) + '_' + str(spec.device)], spec)
|
|
spec = spectral_normalize_torch(spec)
|
|
|
|
return spec
|