Basic pipeline that lowercases and collapses whitespace without transliteration.

Cleans the noise from a speech waveform given a noise profile. The waveform must have the same sampling rate as the one used to create the n

Computes an embedding for a single utterance. # TODO: handle multiple wavs to benefit from batching on GPU :param wav: a preprocessed (s

Pipeline for English text, including number and abbreviation expansion.

Infers the waveform of a mel spectrogram output by the synthesizer (the format must match that of the synthesizer!) :param normaliz

Converts linear spectrogram to waveform using librosa

Converts mel spectrogram to waveform using librosa

Loads the model in memory. If this function is not explicitely called, it will be run on the first call to embed_frames() with the default we

Returns list of ARPAbet pronunciations of the given word.

Compute left and right padding

Applies the preprocessing operations used in training the Speaker Encoder to a waveform either on disk or in memory. The waveform will be re

Creates a profile of the noise in a given waveform. :param noise: a waveform containing noise ONLY, as a numpy array of floats or ints.

Crops the frames into a partial utterance of n_frames :param n_frames: The number of frames of the partial utterance