paddlespeech.t2s.models.melgan.melgan module

MelGAN Modules.

class paddlespeech.t2s.models.melgan.melgan.MelGANDiscriminator(in_channels: int = 1, out_channels: int = 1, kernel_sizes: List[int] = [5, 3], channels: int = 16, max_downsample_channels: int = 1024, bias: bool = True, downsample_scales: List[int] = [4, 4, 4, 4], nonlinear_activation: str = 'leakyrelu', nonlinear_activation_params: Dict[str, Any] = {'negative_slope': 0.2}, pad: str = 'Pad1D', pad_params: Dict[str, Any] = {'mode': 'reflect'}, init_type: str = 'xavier_uniform')

Bases: Layer

MelGAN discriminator 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)	Calculate forward propagation. Args: x (Tensor): Input noise signal (B, 1, T). Returns: List: List of output tensors of each layer (for feat_match_loss).
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)

Calculate forward propagation. Args:

x (Tensor):

Input noise signal (B, 1, T).

Returns:

List: List of output tensors of each layer (for feat_match_loss).

class paddlespeech.t2s.models.melgan.melgan.MelGANGenerator(in_channels: int = 80, out_channels: int = 1, kernel_size: int = 7, channels: int = 512, bias: bool = True, upsample_scales: List[int] = [8, 8, 2, 2], stack_kernel_size: int = 3, stacks: int = 3, nonlinear_activation: str = 'leakyrelu', nonlinear_activation_params: Dict[str, Any] = {'negative_slope': 0.2}, pad: str = 'Pad1D', pad_params: Dict[str, Any] = {'mode': 'reflect'}, use_final_nonlinear_activation: bool = True, use_weight_norm: bool = True, use_causal_conv: bool = False, init_type: str = 'xavier_uniform')

Bases: Layer

MelGAN generator 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.
apply_weight_norm()	Recursively apply weight normalization to all the Convolution layers in the sublayers.
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(c)	Calculate forward propagation.
full_name()	Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__
inference(c)	Perform inference.
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.
remove_weight_norm()	Recursively remove weight normalization from all the Convolution layers in the sublayers.
reset_parameters()	Reset parameters.
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

apply_weight_norm()

Recursively apply weight normalization to all the Convolution layers in the sublayers.

forward(c)

Calculate forward propagation.

Args:

c (Tensor):

Input tensor (B, in_channels, T).

Returns:

Tensor: Output tensor (B, out_channels, T ** prod(upsample_scales)).

inference(c)

Perform inference.

Args:

c (Union[Tensor, ndarray]):

Input tensor (T, in_channels).

Returns:

Tensor: Output tensor (out_channels*T ** prod(upsample_scales), 1).

remove_weight_norm()

Recursively remove weight normalization from all the Convolution layers in the sublayers.

reset_parameters()

Reset parameters. This initialization follows official implementation manner. https://github.com/descriptinc/melgan-neurips/blob/master/mel2wav/modules.py

class paddlespeech.t2s.models.melgan.melgan.MelGANInference(normalizer, melgan_generator)

Bases: Layer

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(logmel)	Defines the computation performed at every call.
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(logmel)

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters:

*inputs(tuple): unpacked tuple arguments **kwargs(dict): unpacked dict arguments

class paddlespeech.t2s.models.melgan.melgan.MelGANMultiScaleDiscriminator(in_channels: int = 1, out_channels: int = 1, scales: int = 3, downsample_pooling: str = 'AvgPool1D', downsample_pooling_params: Dict[str, Any] = {'exclusive': True, 'kernel_size': 4, 'padding': 1, 'stride': 2}, kernel_sizes: List[int] = [5, 3], channels: int = 16, max_downsample_channels: int = 1024, bias: bool = True, downsample_scales: List[int] = [4, 4, 4, 4], nonlinear_activation: str = 'leakyrelu', nonlinear_activation_params: Dict[str, Any] = {'negative_slope': 0.2}, pad: str = 'Pad1D', pad_params: Dict[str, Any] = {'mode': 'reflect'}, use_weight_norm: bool = True, init_type: str = 'xavier_uniform')

Bases: Layer

MelGAN multi-scale discriminator 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.
apply_weight_norm()	Recursively apply weight normalization to all the Convolution layers in the sublayers.
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)	Calculate forward propagation. Args: x (Tensor): Input noise signal (B, 1, T). Returns: List: List of list of each discriminator outputs, which consists of each layer output tensors.
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.
remove_weight_norm()	Recursively remove weight normalization from all the Convolution layers in the sublayers.
reset_parameters()	Reset parameters.
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

apply_weight_norm()

Recursively apply weight normalization to all the Convolution layers in the sublayers.

forward(x)

Calculate forward propagation. Args:

x (Tensor):

Input noise signal (B, 1, T).

Returns:

List: List of list of each discriminator outputs, which consists of each layer output tensors.

remove_weight_norm()

Recursively remove weight normalization from all the Convolution layers in the sublayers.

reset_parameters()

Reset parameters. This initialization follows official implementation manner. https://github.com/descriptinc/melgan-neurips/blob/master/mel2wav/modules.py