espnet.vc package¶

espnet.vc.pytorch_backend.vc¶

E2E VC training / decoding functions.

class espnet.vc.pytorch_backend.vc.CustomConverter[source]¶

Bases: object

Custom converter.

Initilize module.

class espnet.vc.pytorch_backend.vc.CustomEvaluator(model, iterator, target, device)[source]¶

Bases: espnet.utils.training.evaluator.BaseEvaluator

Custom evaluator.

Initilize module.

Parameters:

model (torch.nn.Module) – Pytorch model instance.
iterator (chainer.dataset.Iterator) – Iterator for validation.
target (chainer.Chain) – Dummy chain instance.
device (torch.device) – The device to be used in evaluation.

evaluate()[source]¶: Evaluate over validation iterator.

class espnet.vc.pytorch_backend.vc.CustomUpdater(model, grad_clip, iterator, optimizer, device, accum_grad=1)[source]¶

Bases: chainer.training.updaters.standard_updater.StandardUpdater

Custom updater.

Initilize module.

Parameters:

model (torch.nn.Module) – Pytorch model instance.
grad_clip (float) – The gradient clipping value.
iterator (chainer.dataset.Iterator) – Iterator for training.
optimizer (torch.optim.Optimizer) – Pytorch optimizer instance.
device (torch.device) – The device to be used in training.

update()[source]¶: Run update function.

update_core()[source]¶: Update model one step.

espnet.vc.pytorch_backend.vc.decode(args)[source]¶: Decode with E2E VC model.

espnet.vc.pytorch_backend.vc.train(args)[source]¶: Train E2E VC model.