athena.models.tts.fastspeech2

Module Contents

Classes

FastSpeech2	Reference: FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
DurationCalculator	Calculate duration and outputs based on teacher model
VariantPredictor

class athena.models.tts.fastspeech2.FastSpeech2(data_descriptions, config=None)

Bases: athena.models.tts.fastspeech.FastSpeech

Reference: FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

default_config

call(samples, training: bool = None)

call model

synthesize(samples)

class athena.models.tts.fastspeech2.DurationCalculator(teacher_model=None, teacher_type=None)

Bases: tensorflow.keras.layers.Layer

Calculate duration and outputs based on teacher model

call(samples)

Parameters

samples – samples from dataset

Returns:

durations: Batch of durations shape: [batch, max_input_length).

class athena.models.tts.fastspeech2.VariantPredictor(hparams, **kwargs)

Bases: tensorflow.keras.layers.Layer

call(inputs, training=False)