athena.models.tts.fastspeech2
¶
Module Contents¶
Classes¶
Reference: FastSpeech 2: Fast and High-Quality End-to-End Text to Speech |
|
Calculate duration and outputs based on teacher model |
|
- 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).