paddlespeech.t2s.models.hifigan.hifigan_updater module

class paddlespeech.t2s.models.hifigan.hifigan_updater.HiFiGANEvaluator(models: Dict[str, Layer], criterions: Dict[str, Layer], dataloader: DataLoader, lambda_adv: float = 1.0, lambda_aux: float = 1.0, lambda_feat_match: float = 1.0, output_dir=None)

Bases: StandardEvaluator

Attributes

name

Methods

__call__([trainer])	Main action of the extention.
finalize(trainer)	Action that is executed when training is done.
initialize(trainer)	Action that is executed once to get the corect trainer state.
on_error(trainer, exc, tb)	Handles the error raised during training before finalization.

evaluate
evaluate_core

evaluate_core(batch)

class paddlespeech.t2s.models.hifigan.hifigan_updater.HiFiGANUpdater(models: Dict[str, Layer], optimizers: Dict[str, Optimizer], criterions: Dict[str, Layer], schedulers: Dict[str, LRScheduler], dataloader: DataLoader, generator_train_start_steps: int = 0, discriminator_train_start_steps: int = 100000, lambda_adv: float = 1.0, lambda_aux: float = 1.0, lambda_feat_match: float = 1.0, output_dir=None)

Bases: StandardUpdater

Attributes

updates_per_epoch

Number of updater per epoch, determined by the length of the dataloader.

Methods

new_epoch()	Start a new epoch.
read_batch()	Read a batch from the data loader, auto renew when data is exhausted.
set_state_dict(state_dict)	Set state dict for a Updater.
state_dict()	State dict of a Updater, model, optimizer and updater state are included.
update_core(batch)	A simple case for a training step.

load
save
update

update_core(batch)

A simple case for a training step. Basic assumptions are: Single model; Single optimizer; A batch from the dataloader is just the input of the model; The model return a single loss, or a dict containing serval losses. Parameters updates at every batch, no gradient accumulation.