Model API#

Model API provides you a set of functions that easily make your model compatible with the Trainer, Synthesizer and ModelZoo.

Base TTS Model#

class TTS.tts.models.base_tts.BaseTTS(config, ap, tokenizer, speaker_manager=None, language_manager=None)[source]#

Base tts class. Every new tts model must inherit this.

It defines common tts specific functions on top of Model implementation.

format_batch(batch)[source]#

Generic batch formatting for TTSDataset.

You must override this if you use a custom dataset.

get_aux_input(**kwargs)[source]#: Prepare and return aux_input used by forward()

init_multispeaker(config, data=None)[source]#

Initialize a speaker embedding layer if needen and define expected embedding channel size for defining in_channels size of the connected layers.

This implementation yields 3 possible outcomes:

If config.use_speaker_embedding and `config.use_d_vector_file are False, do nothing.
If config.use_d_vector_file is True, set expected embedding channel size to config.d_vector_dim or 512.

3. If config.use_speaker_embedding, initialize a speaker embedding layer with channel size of config.d_vector_dim or 512.

You can override this function for new models.

on_init_start(trainer)[source]#: Save the speaker.pth and language_ids.json at the beginning of the training. Also update both paths.

test_run(assets)[source]#

Generic test run for tts models used by Trainer.

You can override this for a different behaviour.

Parameters: assets (dict) – A dict of training assets. For tts models, it must include {‘audio_processor’: ap}.
Returns: Test figures and audios to be projected to Tensorboard.
Return type: Tuple[Dict, Dict]

class TTS.vocoder.models.base_vocoder.BaseVocoder(config)[source]#

Base vocoder class. Every new vocoder model must inherit this.

It defines vocoder specific functions on top of Model.

Notes on input/output tensor shapes:

Any input or output tensor of the model must be shaped as