Spaces:
Running
Running
| import torch | |
| import torch.utils.data | |
| import librosa | |
| import logging | |
| logger = logging.getLogger(__name__) | |
| MAX_WAV_VALUE = 32768.0 | |
| def dynamic_range_compression_torch(x, C=1, clip_val=1e-5): | |
| """ | |
| PARAMS | |
| ------ | |
| C: compression factor | |
| """ | |
| return torch.log(torch.clamp(x, min=clip_val) * C) | |
| def dynamic_range_decompression_torch(x, C=1): | |
| """ | |
| PARAMS | |
| ------ | |
| C: compression factor used to compress | |
| """ | |
| 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) | |
| # Reusable banks | |
| mel_basis = {} | |
| hann_window = {} | |
| def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False): | |
| """Convert waveform into Linear-frequency Linear-amplitude spectrogram. | |
| Args: | |
| y :: (B, T) - Audio waveforms | |
| n_fft | |
| sampling_rate | |
| hop_size | |
| win_size | |
| center | |
| Returns: | |
| :: (B, Freq, Frame) - Linear-frequency Linear-amplitude spectrogram | |
| """ | |
| # Window - Cache if needed | |
| 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 | |
| ) | |
| # Padding | |
| 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) | |
| # Complex Spectrogram :: (B, T) -> (B, Freq, Frame, RealComplex=2) | |
| 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, | |
| ) | |
| # Linear-frequency Linear-amplitude spectrogram :: (B, Freq, Frame, RealComplex=2) -> (B, Freq, Frame) | |
| 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): | |
| # MelBasis - Cache if needed | |
| 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.filters.mel( | |
| 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 | |
| ) | |
| # Mel-frequency Log-amplitude spectrogram :: (B, Freq=num_mels, Frame) | |
| 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 | |
| ): | |
| """Convert waveform into Mel-frequency Log-amplitude spectrogram. | |
| Args: | |
| y :: (B, T) - Waveforms | |
| Returns: | |
| melspec :: (B, Freq, Frame) - Mel-frequency Log-amplitude spectrogram | |
| """ | |
| # Linear-frequency Linear-amplitude spectrogram :: (B, T) -> (B, Freq, Frame) | |
| spec = spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center) | |
| # Mel-frequency Log-amplitude spectrogram :: (B, Freq, Frame) -> (B, Freq=num_mels, Frame) | |
| melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax) | |
| return melspec | |