class pumpp.feature.TempoScale(name, sr, hop_length, win_length, n_fmt=128, conv=None)[source]

Tempogram scale transform.

Mellin scale transform magnitude of the Tempogram.


name (str) Name of this extractor
sr (number > 0) Sampling rate of audio
hop_length (int > 0) Hop length for analysis frames
win_length (int > 0) Number of frames per analysis window
n_fmt (int > 0) Number of scale coefficients to retain
__init__(name, sr, hop_length, win_length, n_fmt=128, conv=None)[source]


__init__(name, sr, hop_length, win_length[, ...])
layers() Construct Keras input layers for the given transformer
merge(data) Merge an array of output dictionaries into a single dictionary with properly scoped names.
n_frames(duration) Get the number of frames for a given duration
phase_diff(phase) Compute the phase differential along a given axis
register(key, dimension, dtype[, channels])
scope(key) Apply the name scope to a key
transform(y, sr) Transform an audio signal
transform_audio(y) Apply the scale transform to the tempogram