espnet2.tasks.rst_vocoder.RestorationVocoderTask

source

class espnet2.tasks.rst_vocoder.RestorationVocoderTask

Bases: AbsTask

classmethod add_task_arguments(parser)

classmethod build_collate_fn(args, train)

Return “collate_fn”, which is a callable object and given to DataLoader.

>>> from torch.utils.data import DataLoader
>>> loader = DataLoader(collate_fn=cls.build_collate_fn(args, train=True), ...)

In many cases, you can use our common collate_fn.

classmethod build_model(args)

classmethod build_optimizers(args, model)

classmethod build_preprocess_fn(args, train)

classmethod get_trainer()

num_optimizers : int = 2

classmethod optional_data_names(train=True, inference=False)

Define the optional names by Task

This function is used by

cls.check_task_requirements() If your model is defined as follows,

>>> from espnet2.train.abs_espnet_model import AbsESPnetModel
>>> class Model(AbsESPnetModel):
...     def forward(self, input, output, opt=None):  pass

then “optional_data_names” should be as

>>> optional_data_names = ('opt',)

classmethod required_data_names(train=True, inference=False)

Define the required names by Task

This function is used by

cls.check_task_requirements() If your model is defined as following,

>>> from espnet2.train.abs_espnet_model import AbsESPnetModel
>>> class Model(AbsESPnetModel):
...     def forward(self, input, output, opt=None):  pass

then “required_data_names” should be as

>>> required_data_names = ('input', 'output')

trainer

alias of GANTrainer