paddlespeech.t2s.exps.waveflow.train module

class paddlespeech.t2s.exps.waveflow.train.Experiment(config, args)

Bases: ExperimentBase

Attributes:

parallel

A flag indicating whether the experiment should run with multiprocessing.

Methods

close()	Close visualizer to avoid hanging after training
dump_config()	Save the configuration used for this experiment.
init_parallel()	Init environment for multiprocess training.
new_epoch()	Reset the train loader and increment epoch.
read_batch()	Read a batch from the train_loader.
resume_or_load()	Resume from latest checkpoint at checkpoints in the output directory or load a specified checkpoint.
run()	The routine of the experiment after setup.
save()	Save checkpoint (model parameters and optimizer states).
setup()	Setup the experiment.
setup_checkpointer()	Create a directory used to save checkpoints into.
setup_dataloader()	Setup training dataloader and validation dataloader.
setup_logger()	Initialize a text logger to log the experiment.
setup_model()	Setup model, criterion and optimizer, etc.
setup_output_dir()	Create a directory used for output.
setup_visualizer()	Initialize a visualizer to log the experiment.
train()	The training process.
train_batch()	The training loop.
valid()	The validation.

compute_outputs

compute_outputs(mel, wav)

setup_dataloader()

Setup training dataloader and validation dataloader. A subclass should implement this method.

setup_model()

Setup model, criterion and optimizer, etc. A subclass should implement this method.

train_batch()

The training loop. A subclass should implement this method.

valid()

The validation. A subclass should implement this method.

paddlespeech.t2s.exps.waveflow.train.main(config, args)

paddlespeech.t2s.exps.waveflow.train.main_sp(config, args)