paddlespeech.t2s.models.vits.flow module

Basic Flow modules used in VITS.

This code is based on https://github.com/jaywalnut310/vits.

class paddlespeech.t2s.models.vits.flow.ConvFlow(in_channels: int, hidden_channels: int, kernel_size: int, layers: int, bins: int = 10, tail_bound: float = 5.0)[source]

Bases: Layer

Convolutional flow module.

Methods

__call__(*inputs, **kwargs)

Call self as a function.

add_parameter(name, parameter)

Adds a Parameter instance.

add_sublayer(name, sublayer)

Adds a sub Layer instance.

apply(fn)

Applies fn recursively to every sublayer (as returned by .sublayers()) as well as self.

buffers([include_sublayers])

Returns a list of all buffers from current layer and its sub-layers.

children()

Returns an iterator over immediate children layers.

clear_gradients()

Clear the gradients of all parameters for this layer.

create_parameter(shape[, attr, dtype, ...])

Create parameters for this layer.

create_tensor([name, persistable, dtype])

Create Tensor for this layer.

create_variable([name, persistable, dtype])

Create Tensor for this layer.

eval()

Sets this Layer and all its sublayers to evaluation mode.

extra_repr()

Extra representation of this layer, you can have custom implementation of your own layer.

forward(x, x_mask[, g, inverse])

Calculate forward propagation. Args: x (Tensor): Input tensor (B, channels, T). x_mask (Tensor): Mask tensor (B, 1, T). g (Optional[Tensor]): Global conditioning tensor (B, channels, 1). inverse (bool): Whether to inverse the flow. Returns: Tensor: Output tensor (B, channels, T). Tensor: Log-determinant tensor for NLL (B,) if not inverse.

full_name()

Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__

load_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

named_buffers([prefix, include_sublayers])

Returns an iterator over all buffers in the Layer, yielding tuple of name and Tensor.

named_children()

Returns an iterator over immediate children layers, yielding both the name of the layer as well as the layer itself.

named_parameters([prefix, include_sublayers])

Returns an iterator over all parameters in the Layer, yielding tuple of name and parameter.

named_sublayers([prefix, include_self, ...])

Returns an iterator over all sublayers in the Layer, yielding tuple of name and sublayer.

parameters([include_sublayers])

Returns a list of all Parameters from current layer and its sub-layers.

register_buffer(name, tensor[, persistable])

Registers a tensor as buffer into the layer.

register_forward_post_hook(hook)

Register a forward post-hook for Layer.

register_forward_pre_hook(hook)

Register a forward pre-hook for Layer.

set_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

set_state_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

state_dict([destination, include_sublayers, ...])

Get all parameters and persistable buffers of current layer and its sub-layers.

sublayers([include_self])

Returns a list of sub layers.

to([device, dtype, blocking])

Cast the parameters and buffers of Layer by the give device, dtype and blocking.

to_static_state_dict([destination, ...])

Get all parameters and buffers of current layer and its sub-layers.

train()

Sets this Layer and all its sublayers to training mode.

backward

register_state_dict_hook

forward(x: Tensor, x_mask: Tensor, g: Optional[Tensor] = None, inverse: bool = False) Union[Tensor, Tuple[Tensor, Tensor]][source]

Calculate forward propagation. Args:

x (Tensor):

Input tensor (B, channels, T).

x_mask (Tensor):

Mask tensor (B, 1, T).

g (Optional[Tensor]):

Global conditioning tensor (B, channels, 1).

inverse (bool):

Whether to inverse the flow.

Returns:
Tensor:

Output tensor (B, channels, T).

Tensor:

Log-determinant tensor for NLL (B,) if not inverse.

class paddlespeech.t2s.models.vits.flow.DilatedDepthSeparableConv(channels: int, kernel_size: int, layers: int, dropout_rate: float = 0.0, eps: float = 1e-05)[source]

Bases: Layer

Dilated depth-separable conv module.

Methods

__call__(*inputs, **kwargs)

Call self as a function.

add_parameter(name, parameter)

Adds a Parameter instance.

add_sublayer(name, sublayer)

Adds a sub Layer instance.

apply(fn)

Applies fn recursively to every sublayer (as returned by .sublayers()) as well as self.

buffers([include_sublayers])

Returns a list of all buffers from current layer and its sub-layers.

children()

Returns an iterator over immediate children layers.

clear_gradients()

Clear the gradients of all parameters for this layer.

create_parameter(shape[, attr, dtype, ...])

Create parameters for this layer.

create_tensor([name, persistable, dtype])

Create Tensor for this layer.

create_variable([name, persistable, dtype])

Create Tensor for this layer.

eval()

Sets this Layer and all its sublayers to evaluation mode.

extra_repr()

Extra representation of this layer, you can have custom implementation of your own layer.

forward(x, x_mask[, g])

Calculate forward propagation. Args: x (Tensor): Input tensor (B, in_channels, T). x_mask (Tensor): Mask tensor (B, 1, T). g (Optional[Tensor]): Global conditioning tensor (B, global_channels, 1). Returns: Tensor: Output tensor (B, channels, T).

full_name()

Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__

load_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

named_buffers([prefix, include_sublayers])

Returns an iterator over all buffers in the Layer, yielding tuple of name and Tensor.

named_children()

Returns an iterator over immediate children layers, yielding both the name of the layer as well as the layer itself.

named_parameters([prefix, include_sublayers])

Returns an iterator over all parameters in the Layer, yielding tuple of name and parameter.

named_sublayers([prefix, include_self, ...])

Returns an iterator over all sublayers in the Layer, yielding tuple of name and sublayer.

parameters([include_sublayers])

Returns a list of all Parameters from current layer and its sub-layers.

register_buffer(name, tensor[, persistable])

Registers a tensor as buffer into the layer.

register_forward_post_hook(hook)

Register a forward post-hook for Layer.

register_forward_pre_hook(hook)

Register a forward pre-hook for Layer.

set_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

set_state_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

state_dict([destination, include_sublayers, ...])

Get all parameters and persistable buffers of current layer and its sub-layers.

sublayers([include_self])

Returns a list of sub layers.

to([device, dtype, blocking])

Cast the parameters and buffers of Layer by the give device, dtype and blocking.

to_static_state_dict([destination, ...])

Get all parameters and buffers of current layer and its sub-layers.

train()

Sets this Layer and all its sublayers to training mode.

backward

register_state_dict_hook

forward(x: Tensor, x_mask: Tensor, g: Optional[Tensor] = None) Tensor[source]

Calculate forward propagation. Args:

x (Tensor):

Input tensor (B, in_channels, T).

x_mask (Tensor):

Mask tensor (B, 1, T).

g (Optional[Tensor]):

Global conditioning tensor (B, global_channels, 1).

Returns:
Tensor:

Output tensor (B, channels, T).

class paddlespeech.t2s.models.vits.flow.ElementwiseAffineFlow(channels: int)[source]

Bases: Layer

Elementwise affine flow module.

Methods

__call__(*inputs, **kwargs)

Call self as a function.

add_parameter(name, parameter)

Adds a Parameter instance.

add_sublayer(name, sublayer)

Adds a sub Layer instance.

apply(fn)

Applies fn recursively to every sublayer (as returned by .sublayers()) as well as self.

buffers([include_sublayers])

Returns a list of all buffers from current layer and its sub-layers.

children()

Returns an iterator over immediate children layers.

clear_gradients()

Clear the gradients of all parameters for this layer.

create_parameter(shape[, attr, dtype, ...])

Create parameters for this layer.

create_tensor([name, persistable, dtype])

Create Tensor for this layer.

create_variable([name, persistable, dtype])

Create Tensor for this layer.

eval()

Sets this Layer and all its sublayers to evaluation mode.

extra_repr()

Extra representation of this layer, you can have custom implementation of your own layer.

forward(x, x_mask[, inverse])

Calculate forward propagation. Args: x (Tensor): Input tensor (B, channels, T). x_mask (Tensor): Mask tensor (B, 1, T). inverse (bool): Whether to inverse the flow. Returns: Tensor: Output tensor (B, channels, T). Tensor: Log-determinant tensor for NLL (B,) if not inverse.

full_name()

Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__

load_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

named_buffers([prefix, include_sublayers])

Returns an iterator over all buffers in the Layer, yielding tuple of name and Tensor.

named_children()

Returns an iterator over immediate children layers, yielding both the name of the layer as well as the layer itself.

named_parameters([prefix, include_sublayers])

Returns an iterator over all parameters in the Layer, yielding tuple of name and parameter.

named_sublayers([prefix, include_self, ...])

Returns an iterator over all sublayers in the Layer, yielding tuple of name and sublayer.

parameters([include_sublayers])

Returns a list of all Parameters from current layer and its sub-layers.

register_buffer(name, tensor[, persistable])

Registers a tensor as buffer into the layer.

register_forward_post_hook(hook)

Register a forward post-hook for Layer.

register_forward_pre_hook(hook)

Register a forward pre-hook for Layer.

set_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

set_state_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

state_dict([destination, include_sublayers, ...])

Get all parameters and persistable buffers of current layer and its sub-layers.

sublayers([include_self])

Returns a list of sub layers.

to([device, dtype, blocking])

Cast the parameters and buffers of Layer by the give device, dtype and blocking.

to_static_state_dict([destination, ...])

Get all parameters and buffers of current layer and its sub-layers.

train()

Sets this Layer and all its sublayers to training mode.

backward

register_state_dict_hook

forward(x: Tensor, x_mask: Tensor, inverse: bool = False, **kwargs) Union[Tensor, Tuple[Tensor, Tensor]][source]

Calculate forward propagation. Args:

x (Tensor):

Input tensor (B, channels, T).

x_mask (Tensor):

Mask tensor (B, 1, T).

inverse (bool):

Whether to inverse the flow.

Returns:
Tensor:

Output tensor (B, channels, T).

Tensor:

Log-determinant tensor for NLL (B,) if not inverse.

class paddlespeech.t2s.models.vits.flow.FlipFlow(name_scope=None, dtype='float32')[source]

Bases: Layer

Flip flow module.

Methods

__call__(*inputs, **kwargs)

Call self as a function.

add_parameter(name, parameter)

Adds a Parameter instance.

add_sublayer(name, sublayer)

Adds a sub Layer instance.

apply(fn)

Applies fn recursively to every sublayer (as returned by .sublayers()) as well as self.

buffers([include_sublayers])

Returns a list of all buffers from current layer and its sub-layers.

children()

Returns an iterator over immediate children layers.

clear_gradients()

Clear the gradients of all parameters for this layer.

create_parameter(shape[, attr, dtype, ...])

Create parameters for this layer.

create_tensor([name, persistable, dtype])

Create Tensor for this layer.

create_variable([name, persistable, dtype])

Create Tensor for this layer.

eval()

Sets this Layer and all its sublayers to evaluation mode.

extra_repr()

Extra representation of this layer, you can have custom implementation of your own layer.

forward(x, *args[, inverse])

Calculate forward propagation. Args: x (Tensor): Input tensor (B, channels, T). inverse (bool): Whether to inverse the flow. Returns: Tensor: Flipped tensor (B, channels, T). Tensor: Log-determinant tensor for NLL (B,) if not inverse.

full_name()

Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__

load_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

named_buffers([prefix, include_sublayers])

Returns an iterator over all buffers in the Layer, yielding tuple of name and Tensor.

named_children()

Returns an iterator over immediate children layers, yielding both the name of the layer as well as the layer itself.

named_parameters([prefix, include_sublayers])

Returns an iterator over all parameters in the Layer, yielding tuple of name and parameter.

named_sublayers([prefix, include_self, ...])

Returns an iterator over all sublayers in the Layer, yielding tuple of name and sublayer.

parameters([include_sublayers])

Returns a list of all Parameters from current layer and its sub-layers.

register_buffer(name, tensor[, persistable])

Registers a tensor as buffer into the layer.

register_forward_post_hook(hook)

Register a forward post-hook for Layer.

register_forward_pre_hook(hook)

Register a forward pre-hook for Layer.

set_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

set_state_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

state_dict([destination, include_sublayers, ...])

Get all parameters and persistable buffers of current layer and its sub-layers.

sublayers([include_self])

Returns a list of sub layers.

to([device, dtype, blocking])

Cast the parameters and buffers of Layer by the give device, dtype and blocking.

to_static_state_dict([destination, ...])

Get all parameters and buffers of current layer and its sub-layers.

train()

Sets this Layer and all its sublayers to training mode.

backward

register_state_dict_hook

forward(x: Tensor, *args, inverse: bool = False, **kwargs) Union[Tensor, Tuple[Tensor, Tensor]][source]

Calculate forward propagation. Args:

x (Tensor):

Input tensor (B, channels, T).

inverse (bool):

Whether to inverse the flow.

Returns:
Tensor:

Flipped tensor (B, channels, T).

Tensor:

Log-determinant tensor for NLL (B,) if not inverse.

class paddlespeech.t2s.models.vits.flow.LogFlow(name_scope=None, dtype='float32')[source]

Bases: Layer

Log flow module.

Methods

__call__(*inputs, **kwargs)

Call self as a function.

add_parameter(name, parameter)

Adds a Parameter instance.

add_sublayer(name, sublayer)

Adds a sub Layer instance.

apply(fn)

Applies fn recursively to every sublayer (as returned by .sublayers()) as well as self.

buffers([include_sublayers])

Returns a list of all buffers from current layer and its sub-layers.

children()

Returns an iterator over immediate children layers.

clear_gradients()

Clear the gradients of all parameters for this layer.

create_parameter(shape[, attr, dtype, ...])

Create parameters for this layer.

create_tensor([name, persistable, dtype])

Create Tensor for this layer.

create_variable([name, persistable, dtype])

Create Tensor for this layer.

eval()

Sets this Layer and all its sublayers to evaluation mode.

extra_repr()

Extra representation of this layer, you can have custom implementation of your own layer.

forward(x, x_mask[, inverse, eps])

Calculate forward propagation. Args: x (Tensor): Input tensor (B, channels, T). x_mask (Tensor): Mask tensor (B, 1, T). inverse (bool): Whether to inverse the flow. eps (float): Epsilon for log. Returns: Tensor: Output tensor (B, channels, T). Tensor: Log-determinant tensor for NLL (B,) if not inverse.

full_name()

Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__

load_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

named_buffers([prefix, include_sublayers])

Returns an iterator over all buffers in the Layer, yielding tuple of name and Tensor.

named_children()

Returns an iterator over immediate children layers, yielding both the name of the layer as well as the layer itself.

named_parameters([prefix, include_sublayers])

Returns an iterator over all parameters in the Layer, yielding tuple of name and parameter.

named_sublayers([prefix, include_self, ...])

Returns an iterator over all sublayers in the Layer, yielding tuple of name and sublayer.

parameters([include_sublayers])

Returns a list of all Parameters from current layer and its sub-layers.

register_buffer(name, tensor[, persistable])

Registers a tensor as buffer into the layer.

register_forward_post_hook(hook)

Register a forward post-hook for Layer.

register_forward_pre_hook(hook)

Register a forward pre-hook for Layer.

set_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

set_state_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

state_dict([destination, include_sublayers, ...])

Get all parameters and persistable buffers of current layer and its sub-layers.

sublayers([include_self])

Returns a list of sub layers.

to([device, dtype, blocking])

Cast the parameters and buffers of Layer by the give device, dtype and blocking.

to_static_state_dict([destination, ...])

Get all parameters and buffers of current layer and its sub-layers.

train()

Sets this Layer and all its sublayers to training mode.

backward

register_state_dict_hook

forward(x: Tensor, x_mask: Tensor, inverse: bool = False, eps: float = 1e-05, **kwargs) Union[Tensor, Tuple[Tensor, Tensor]][source]

Calculate forward propagation. Args:

x (Tensor):

Input tensor (B, channels, T).

x_mask (Tensor):

Mask tensor (B, 1, T).

inverse (bool):

Whether to inverse the flow.

eps (float):

Epsilon for log.

Returns:
Tensor:

Output tensor (B, channels, T).

Tensor:

Log-determinant tensor for NLL (B,) if not inverse.

class paddlespeech.t2s.models.vits.flow.Transpose(dim1: int, dim2: int)[source]

Bases: Layer

Transpose module for paddle.nn.Sequential().

Methods

__call__(*inputs, **kwargs)

Call self as a function.

add_parameter(name, parameter)

Adds a Parameter instance.

add_sublayer(name, sublayer)

Adds a sub Layer instance.

apply(fn)

Applies fn recursively to every sublayer (as returned by .sublayers()) as well as self.

buffers([include_sublayers])

Returns a list of all buffers from current layer and its sub-layers.

children()

Returns an iterator over immediate children layers.

clear_gradients()

Clear the gradients of all parameters for this layer.

create_parameter(shape[, attr, dtype, ...])

Create parameters for this layer.

create_tensor([name, persistable, dtype])

Create Tensor for this layer.

create_variable([name, persistable, dtype])

Create Tensor for this layer.

eval()

Sets this Layer and all its sublayers to evaluation mode.

extra_repr()

Extra representation of this layer, you can have custom implementation of your own layer.

forward(x)

Transpose.

full_name()

Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__

load_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

named_buffers([prefix, include_sublayers])

Returns an iterator over all buffers in the Layer, yielding tuple of name and Tensor.

named_children()

Returns an iterator over immediate children layers, yielding both the name of the layer as well as the layer itself.

named_parameters([prefix, include_sublayers])

Returns an iterator over all parameters in the Layer, yielding tuple of name and parameter.

named_sublayers([prefix, include_self, ...])

Returns an iterator over all sublayers in the Layer, yielding tuple of name and sublayer.

parameters([include_sublayers])

Returns a list of all Parameters from current layer and its sub-layers.

register_buffer(name, tensor[, persistable])

Registers a tensor as buffer into the layer.

register_forward_post_hook(hook)

Register a forward post-hook for Layer.

register_forward_pre_hook(hook)

Register a forward pre-hook for Layer.

set_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

set_state_dict(state_dict[, use_structured_name])

Set parameters and persistable buffers from state_dict.

state_dict([destination, include_sublayers, ...])

Get all parameters and persistable buffers of current layer and its sub-layers.

sublayers([include_self])

Returns a list of sub layers.

to([device, dtype, blocking])

Cast the parameters and buffers of Layer by the give device, dtype and blocking.

to_static_state_dict([destination, ...])

Get all parameters and buffers of current layer and its sub-layers.

train()

Sets this Layer and all its sublayers to training mode.

backward

register_state_dict_hook

forward(x: Tensor) Tensor[source]

Transpose.