Shortcuts

torchaudio.prototype.functional

barkscale_fbanks

torchaudio.prototype.functional.barkscale_fbanks(n_freqs: int, f_min: float, f_max: float, n_barks: int, sample_rate: int, bark_scale: str = 'traunmuller') Tensor[source]

Create a frequency bin conversion matrix.

This feature supports the following devices: CPU This API supports the following properties: TorchScript Visualization of generated filter bank
Parameters:
  • n_freqs (int) – Number of frequencies to highlight/apply

  • f_min (float) – Minimum frequency (Hz)

  • f_max (float) – Maximum frequency (Hz)

  • n_barks (int) – Number of mel filterbanks

  • sample_rate (int) – Sample rate of the audio waveform

  • bark_scale (str, optional) – Scale to use: traunmuller,``schroeder`` or wang. (Default: traunmuller)

Returns:

Triangular filter banks (fb matrix) of size (n_freqs, n_barks) meaning number of frequencies to highlight/apply to x the number of filterbanks. Each column is a filterbank so that assuming there is a matrix A of size (…, n_freqs), the applied result would be A * barkscale_fbanks(A.size(-1), ...).

Return type:

torch.Tensor

DSP

adsr_envelope

Generate ADSR Envelope

filter_waveform

Applies filters along time axis of the given waveform.

extend_pitch

Extend the given time series values with multipliers of them.

oscillator_bank

Synthesize waveform from the given instantaneous frequencies and amplitudes.

sinc_impulse_response

Create windowed-sinc impulse response for given cutoff frequencies.

frequency_impulse_response

Create filter from desired frequency response

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources