nnAudio.Spectrogram.DFT¶
- class nnAudio.Spectrogram.DFT(n_fft=2048, freq_bins=None, hop_length=512, window='hann', freq_scale='no', center=True, pad_mode='reflect', fmin=50, fmax=6000, sr=22050)¶
Bases:
torch.nn.modules.module.Module
Experimental feature before torch.fft was made avaliable. The inverse function only works for 1 single frame. i.e. input shape = (batch, n_fft, 1)
Methods
__init__
Initializes internal Module state, shared by both nn.Module and ScriptModule.
Convert a batch of waveforms to spectrums.
Convert a batch of waveforms to CQT spectrograms.
- forward(x)¶
Convert a batch of waveforms to spectrums.
- Parameters
x (torch tensor) –
Input signal should be in either of the following shapes.
(len_audio)
(num_audio, len_audio)
3.
(num_audio, 1, len_audio)
It will be automatically broadcast to the right shape
- inverse(x_real, x_imag)¶
Convert a batch of waveforms to CQT spectrograms.
- Parameters
x_real (torch tensor) – Real part of the signal.
x_imag (torch tensor) – Imaginary part of the signal.