conformer_u2_layer

the transformer model

Module Contents

Classes

ConformerU2EncoderLayer	TransformerEncoderLayer is made up of self-attn and feedforward network.
ConformerU2DecoderLayer	ConformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.

class conformer_u2_layer.ConformerU2EncoderLayer(d_model, nhead, cnn_module_kernel=15, dim_feedforward=2048, dropout=0.1, activation='gelu')

Bases: tensorflow.keras.layers.Layer

TransformerEncoderLayer is made up of self-attn and feedforward network. This standard encoder layer is based on the paper “Attention Is All You Need”. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 6000-6010. Users may modify or implement in a different way during application. :param d_model: the number of expected features in the input (required). :param nhead: the number of heads in the multiheadattention models (required). :param dim_feedforward: the dimension of the feedforward network model (default=2048). :param dropout: the dropout value (default=0.1). :param activation: the activation function of intermediate layer, relu or gelu (default=relu).

Examples::

>>> encoder_layer = ConformerU2EncoderLayer(d_model=512, nhead=8)
>>> src = tf.random(10, 32, 512)
>>> out = encoder_layer(src)

call(src: tensorflow.Tensor, src_mask: Optional[tensorflow.Tensor] = None, mask_pad: Optional[tensorflow.Tensor] = None, output_cache: Optional[tensorflow.Tensor] = None, cnn_cache: Optional[tensorflow.Tensor] = None, training: Optional[bool] = None)

Pass the input through the encoder layer.

Parameters

• src – the sequence to the encoder layer (required).

• src_mask – tf.zeros([1, 0, 256], dtype=tf.float32) the mask for the src sequence (optional).

class conformer_u2_layer.ConformerU2DecoderLayer(d_model, nhead, dim_feedforward=2048, dropout=0.1, activation='gelu')

Bases: tensorflow.keras.layers.Layer

ConformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network. This standard decoder layer is based on the paper “Attention Is All You Need”. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 6000-6010. Users may modify or implement in a different way during application. :param d_model: the number of expected features in the input (required). :param nhead: the number of heads in the multiheadattention models (required). :param dim_feedforward: the dimension of the feedforward network model (default=2048). :param dropout: the dropout value (default=0.1). :param activation: the activation function of intermediate layer, relu or gelu (default=relu).

Examples::

>>> decoder_layer = ConformerU2DecoderLayer(d_model=512, nhead=8)
>>> memory = tf.random(10, 32, 512)
>>> tgt = tf.random(20, 32, 512)
>>> out = decoder_layer(tgt, memory)

call(tgt, memory, tgt_mask=None, memory_mask=None, training=None)

Pass the inputs (and mask) through the decoder layer.

Parameters

• tgt – the sequence to the decoder layer (required).

• memory – the sequence from the last layer of the encoder (required).

• tgt_mask – the mask for the tgt sequence (optional).

• memory_mask – the mask for the memory sequence (optional).