:py:mod:`tonic.audio_augmentations` =================================== .. py:module:: tonic.audio_augmentations Module Contents --------------- Classes ~~~~~~~ .. autoapisummary:: tonic.audio_augmentations.RandomTimeStretch tonic.audio_augmentations.RandomPitchShift tonic.audio_augmentations.RandomAmplitudeScale tonic.audio_augmentations.AddWhiteNoise tonic.audio_augmentations.RIR .. py:class:: RandomTimeStretch Time-stretch an audio sample by a fixed rate. :param samplerate: sample rate of the sample :type samplerate: float :param sample_length: sample length in seconds :type sample_length: int :param factors: range of desired factors for time stretch :type factors: float :param aug_index: index of the chosen factor for time stretch. It will be randomly chosen from the desired range (if not passed while initilization) :type aug_index: int :param caching: if we are caching the DiskCached dataset will dynamically pass copy index of data item to the transform (to set aug_index). Otherwise the aug_index will be chosen randomly in every call of transform :type caching: bool :param fix_length: if True, time stretched signal will be returned in a fixed length (samplerate * sample_length ) :type fix_length: bool :param audio: data sample :type audio: np.ndarray :returns: time stretched data sample :rtype: np.ndarray .. py:attribute:: samplerate :type: float .. py:attribute:: sample_length :type: int .. py:attribute:: factors :type: list .. py:attribute:: aug_index :type: int :value: 0 .. py:attribute:: caching :type: bool :value: False .. py:attribute:: fix_length :type: bool :value: True .. py:method:: __call__(audio: numpy.ndarray) .. py:class:: RandomPitchShift Shift the pitch of a waveform by n_steps steps . :param samplerate: sample rate of the sample :type samplerate: float :param factors: range of desired factors for pitch shift :type factors: float :param aug_index: index of the chosen factor for pitchshift. It will be randomly chosen from the desired range (if not passed while initilization) :type aug_index: int :param caching: if we are caching, the DiskCached dataset will dynamically pass copy index of data item to the transform (to set aug_index). Otherwise the aug_index will be chosen randomly in every call of transform :type caching: bool :param audio: data sample :type audio: np.ndarray :returns: pitch shifted data sample :rtype: np.ndarray .. py:attribute:: samplerate :type: float .. py:attribute:: factors :type: list .. py:attribute:: aug_index :type: int :value: 0 .. py:attribute:: caching :type: bool :value: False .. py:method:: __call__(audio: numpy.ndarray) .. py:class:: RandomAmplitudeScale Scales the maximum amplitude of the incoming signal to a random amplitude chosen from a range. :param samplerate: sample rate of the sample :type samplerate: float :param min_amp: minimum of the amplitude range in volts :type min_amp: float :param max_amp: maximum of the amplitude range in volts :type max_amp: float :param factors: range of desired factors for amplitude scaling :type factors: float :param aug_index: index of the chosen factor for pitchshift. It will be randomly chosen from the desired range (if not passed while initilization) :type aug_index: int :param caching: if we are caching, the DiskCached dataset will dynamically pass copy index of data item to the transform (to set aug_index). Otherwise the aug_index will be chosen randomly in every call of transform :type caching: bool :param data: input (single-or multi-channel) signal. :type data: np.ndarray :returns: scaled version of the signal. :rtype: np.ndarray .. py:attribute:: samplerate :type: float .. py:attribute:: min_amp :type: float :value: 0.058 .. py:attribute:: max_amp :type: float :value: 0.159 .. py:attribute:: factors :type: list .. py:attribute:: aug_index :type: int :value: 0 .. py:attribute:: caching :type: bool :value: False .. py:method:: __post_init__() .. py:method:: __call__(audio: numpy.ndarray) .. py:class:: AddWhiteNoise Add white noise to the data sample with a known ratio. :param samplerate: sample rate of the sample :type samplerate: float :param factors: range of desired ratios for added noise :type factors: float :param aug_index: index of the chosen factor for noise. It will be randomly chosen from the desired range (if not passed while initilization) :type aug_index: int :param caching: if we are caching the DiskCached dataset will dynamically pass copy index of data item to the transform (to set aug_index). Otherwise the aug_index will be chosen randomly in every call of transform :type caching: bool :param audio: data sample :type audio: np.ndarray :returns: data sample with added noise :rtype: np.ndarray .. py:attribute:: samplerate :type: float .. py:attribute:: factors :type: list .. py:attribute:: aug_index :type: int :value: 0 .. py:attribute:: caching :type: bool :value: False .. py:method:: __call__(audio: numpy.ndarray) .. py:class:: RIR Convolves a RIR (room impluse response) to the data sample. :param samplerate: sample rate of the sample :type samplerate: float :param rir_audio: path to a sample room impluse response in the .wav format :type rir_audio: str :param caching: if we are caching the DiskCached dataset will dynamically pass copy index of data item to the transform (to set aug_index). Otherwise the aug_index will be chosen randomly in every call of transform :type caching: bool :param audio: data sample :type audio: np.ndarray :returns: data sample convolved with RIR :rtype: np.ndarray .. py:attribute:: samplerate :type: float .. py:attribute:: rir_audio :type: str .. py:attribute:: caching :type: bool :value: False .. py:method:: __call__(audio)