transform_time_stretch {torchaudio} | R Documentation |
Time Stretch
Description
Stretch stft in time without modifying pitch for a given rate.
Usage
transform_time_stretch(hop_length = NULL, n_freq = 201, fixed_rate = NULL)
Arguments
hop_length |
(int or NULL, optional): Length of hop between STFT windows. (Default: |
n_freq |
(int, optional): number of filter banks from stft. (Default: |
fixed_rate |
(float or NULL, optional): rate to speed up or slow down by.
If NULL is provided, rate must be passed to the forward method. (Default: |
Details
forward param: complex_specgrams (Tensor): complex spectrogram (..., freq, time, complex=2).
overriding_rate (float or NULL, optional): speed up to apply to this batch.
If no rate is passed, use self$fixed_rate
. (Default: NULL
)
Value
Tensor: Stretched complex spectrogram of dimension (..., freq, ceil(time/rate), complex=2).
[Package torchaudio version 0.3.1 Index]