paddlespeech.s2t.modules.embedding module

Positonal Encoding Module.

class paddlespeech.s2t.modules.embedding.NoPositionalEncoding(d_model: int, dropout_rate: float, max_len: int = 5000, reverse: bool = False)

Bases: Layer, PositionalEncodingInterface

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[, offset])	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.
position_encoding(offset, size)	For getting encoding in a streaming fashion Args: offset (int): start offset size (int): requried size of position encoding Returns: paddle.Tensor: Corresponding position encoding
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, offset: int = 0) → Tuple[Tensor, Tensor]

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

Parameters:

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

position_encoding(offset: int, size: int) → Tensor

For getting encoding in a streaming fashion Args:

offset (int): start offset size (int): requried size of position encoding

Returns:

paddle.Tensor: Corresponding position encoding

class paddlespeech.s2t.modules.embedding.PositionalEncoding(d_model: int, dropout_rate: float, max_len: int = 5000, reverse: bool = False)

Bases: Layer, PositionalEncodingInterface

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[, offset])	Add positional encoding. Args: x (paddle.Tensor): Input. Its shape is (batch, time, ...) offset (int): position offset Returns: paddle.Tensor: Encoded tensor. Its shape is (batch, time, ...) paddle.Tensor: for compatibility to RelPositionalEncoding, (batch=1, time, ...).
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.
position_encoding(offset, size)	For getting encoding in a streaming fashion Attention!!!!! we apply dropout only once at the whole utterance level in a none streaming way, but will call this function several times with increasing input size in a streaming scenario, so the dropout will be applied several times. Args: offset (int): start offset size (int): requried size of position encoding Returns: paddle.Tensor: Corresponding position encoding, #[1, T, D].
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, offset: int = 0) → Tuple[Tensor, Tensor]

Add positional encoding. Args:

x (paddle.Tensor): Input. Its shape is (batch, time, ...) offset (int): position offset

Returns:

paddle.Tensor: Encoded tensor. Its shape is (batch, time, ...) paddle.Tensor: for compatibility to RelPositionalEncoding, (batch=1, time, ...)

position_encoding(offset: int, size: int) → Tensor

For getting encoding in a streaming fashion Attention!!!!! we apply dropout only once at the whole utterance level in a none streaming way, but will call this function several times with increasing input size in a streaming scenario, so the dropout will be applied several times. Args:

offset (int): start offset size (int): requried size of position encoding

Returns:

paddle.Tensor: Corresponding position encoding, #[1, T, D].

class paddlespeech.s2t.modules.embedding.PositionalEncodingInterface

Bases: object

Methods

forward(x[, offset])	Compute positional encoding. Args: x (paddle.Tensor): Input tensor (batch, time, *). Returns: paddle.Tensor: Encoded tensor (batch, time, *). paddle.Tensor: Positional embedding tensor (1, time, *).
position_encoding(offset, size)	For getting encoding in a streaming fashion Args: offset (int): start offset size (int): requried size of position encoding Returns: paddle.Tensor: Corresponding position encoding

forward(x: Tensor, offset: int = 0) → Tuple[Tensor, Tensor]

Compute positional encoding. Args:

x (paddle.Tensor): Input tensor (batch, time, *).

Returns:

paddle.Tensor: Encoded tensor (batch, time, *). paddle.Tensor: Positional embedding tensor (1, time, *).

position_encoding(offset: int, size: int) → Tensor

For getting encoding in a streaming fashion Args:

offset (int): start offset size (int): requried size of position encoding

Returns:

paddle.Tensor: Corresponding position encoding

class paddlespeech.s2t.modules.embedding.RelPositionalEncoding(d_model: int, dropout_rate: float, max_len: int = 5000)

Bases: PositionalEncoding

Relative positional encoding module. See : Appendix B in https://arxiv.org/abs/1901.02860

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[, offset])	Compute positional encoding. Args: x (paddle.Tensor): Input tensor (batch, time, *). Returns: paddle.Tensor: Encoded tensor (batch, time, *). paddle.Tensor: Positional embedding tensor (1, time, *).
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.
position_encoding(offset, size)	For getting encoding in a streaming fashion Attention!!!!! we apply dropout only once at the whole utterance level in a none streaming way, but will call this function several times with increasing input size in a streaming scenario, so the dropout will be applied several times. Args: offset (int): start offset size (int): requried size of position encoding Returns: paddle.Tensor: Corresponding position encoding, #[1, T, D].
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, offset: int = 0) → Tuple[Tensor, Tensor]

Compute positional encoding. Args:

x (paddle.Tensor): Input tensor (batch, time, *).

Returns:

paddle.Tensor: Encoded tensor (batch, time, *). paddle.Tensor: Positional embedding tensor (1, time, *).