paddlespeech.t2s.modules.tacotron2.decoder module

Tacotron2 decoder related modules.

class paddlespeech.t2s.modules.tacotron2.decoder.Decoder(idim, odim, att, dlayers=2, dunits=1024, prenet_layers=2, prenet_units=256, postnet_layers=5, postnet_chans=512, postnet_filts=5, output_activation_fn=None, cumulate_att_w=True, use_batch_norm=True, use_concate=True, dropout_rate=0.5, zoneout_rate=0.1, reduction_factor=1)

Bases: Layer

Decoder module of Spectrogram prediction network. This is a module of decoder of Spectrogram prediction network in Tacotron2, which described in `Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions`_. The decoder generates the sequence of features from the sequence of the hidden states. .. Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions:

https://arxiv.org/abs/1712.05884

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.
calculate_all_attentions(hs, hlens, ys)	Calculate all of the attention weights.
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(hs, hlens, ys)	Calculate forward propagation.
full_name()	Full name for this layer, composed by name_scope + "/" + MyLayer.__class__.__name__
inference(h[, threshold, minlenratio, ...])	Generate the sequence of features given the sequences of characters.
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

calculate_all_attentions(hs, hlens, ys)

Calculate all of the attention weights.

Args:

hs (Tensor):

Batch of the sequences of padded hidden states (B, Tmax, idim).

hlens (Tensor(int64)):

Batch of lengths of each input batch (B,).

ys (Tensor):

Batch of the sequences of padded target features (B, Lmax, odim).

Returns:

numpy.ndarray:

Batch of attention weights (B, Lmax, Tmax).

Note:

This computation is performed in teacher-forcing manner.

forward(hs, hlens, ys)

Calculate forward propagation.

Args:

hs (Tensor):

Batch of the sequences of padded hidden states (B, Tmax, idim).

hlens (Tensor(int64) padded):

Batch of lengths of each input batch (B,).

ys (Tensor):

Batch of the sequences of padded target features (B, Lmax, odim).

Returns:

Tensor:

Batch of output tensors after postnet (B, Lmax, odim).

Tensor:

Batch of output tensors before postnet (B, Lmax, odim).

Tensor:

Batch of logits of stop prediction (B, Lmax).

Tensor:

Batch of attention weights (B, Lmax, Tmax).

Note:

This computation is performed in teacher-forcing manner.

inference(h, threshold=0.5, minlenratio=0.0, maxlenratio=10.0, use_att_constraint=False, backward_window=None, forward_window=None)

Generate the sequence of features given the sequences of characters.

Args:

h(Tensor):

Input sequence of encoder hidden states (T, C).

threshold(float, optional, optional):

Threshold to stop generation. (Default value = 0.5)

minlenratio(float, optional, optional):

Minimum length ratio. If set to 1.0 and the length of input is 10, the minimum length of outputs will be 10 * 1 = 10. (Default value = 0.0)

maxlenratio(float, optional, optional):

Minimum length ratio. If set to 10 and the length of input is 10,

the maximum length of outputs will be 10 * 10 = 100. (Default value = 0.0)

use_att_constraint(bool, optional):

Whether to apply attention constraint introduced in Deep Voice 3. (Default value = False)

backward_window(int, optional):

Backward window size in attention constraint. (Default value = None)

forward_window(int, optional):

(Default value = None)

Returns:

Tensor:

Output sequence of features (L, odim).

Tensor:

Output sequence of stop probabilities (L,).

Tensor:

Attention weights (L, T).

Note:

This computation is performed in auto-regressive manner.

class paddlespeech.t2s.modules.tacotron2.decoder.Postnet(idim, odim, n_layers=5, n_chans=512, n_filts=5, dropout_rate=0.5, use_batch_norm=True)

Bases: Layer

Postnet module for Spectrogram prediction network.

This is a module of Postnet in Spectrogram prediction network, which described in `Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions`_. The Postnet predicts refines the predicted Mel-filterbank of the decoder, which helps to compensate the detail sturcture of spectrogram.

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(xs)	Calculate forward propagation.
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(xs)

Calculate forward propagation.

Args:

xs (Tensor): Batch of the sequences of padded input tensors (B, idim, Tmax).

Returns:

Tensor: Batch of padded output tensor. (B, odim, Tmax).

class paddlespeech.t2s.modules.tacotron2.decoder.Prenet(idim, n_layers=2, n_units=256, dropout_rate=0.5)

Bases: Layer

Prenet module for decoder of Spectrogram prediction network.

This is a module of Prenet in the decoder of Spectrogram prediction network, which described in `Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions`_. The Prenet preforms nonlinear conversion of inputs before input to auto-regressive lstm, which helps to learn diagonal attentions.

Notes

This module alway applies dropout even in evaluation. See the detail in `Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions`_.

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.
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):

Batch of input tensors (B, ..., idim).

Returns:

Tensor: Batch of output tensors (B, ..., odim).

class paddlespeech.t2s.modules.tacotron2.decoder.ZoneOutCell(cell, zoneout_rate=0.1)

Bases: Layer

ZoneOut Cell module. This is a module of zoneout described in Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations. This code is modified from eladhoffer/seq2seq.pytorch. Examples ----------

>>> lstm = paddle.nn.LSTMCell(16, 32)
>>> lstm = ZoneOutCell(lstm, 0.5)

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(inputs, hidden)	Calculate forward propagation.
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(inputs, hidden)

Calculate forward propagation.

Args:

inputs (Tensor):

Batch of input tensor (B, input_size).

hidden (tuple):

• Tensor: Batch of initial hidden states (B, hidden_size).

• Tensor: Batch of initial cell states (B, hidden_size).

Returns:

Tensor:

Batch of next hidden states (B, hidden_size).

tuple:

• Tensor: Batch of next hidden states (B, hidden_size).

• Tensor: Batch of next cell states (B, hidden_size).