Args: inputs: A 3-D tensor with shape of [batch, time, depth]. filters: An int. Number of outputs (=activation maps) size: An i

Applies a GRU. Args: inputs: A 3d tensor with shape of [N, T, C]. num_units: An int. The number of hidden units. bidirectio

Applies {batch|layer} normalization. Args: inputs: A tensor with 2 or more dimensions, where the first dimension has `batch_siz

Embeds a given tensor. Args: inputs: A `Tensor` with type `int32` or `int64` containing the ids to be looked up in `lookup ta

Prenet for Encoder and Decoder. Args: inputs: A 3D tensor of shape [N, T, hp.embed_size]. is_training: A boolean. scope: Optiona

Fetch the value from slice queues, then enqueue them again.

Applies a GRU to `inputs`, while attending `memory`. Args: inputs: A 3d tensor with shape of [N, T', C']. Decoder inputs. memory: A 3d

Applies a series of conv1d separately. Args: inputs: A 3d tensor with shape of [N, T, C] K: An int. The size of conv1d banks. Tha

Args: decoder_inputs: A 3d tensor with shape of [N, T', C'], where C'=hp.n_mels*hp.r, dtype of float32. Shifted melspectrogram of

Args: inputs: A 2d tensor with shape of [N, T], dtype of int32. is_training: Whether or not the layer is in training mode. scop

Loads training data and put them in queues

Highway networks, see https://arxiv.org/abs/1505.00387 Args: inputs: A 3D tensor of shape [N, T, W]. num_units: An int or `None`. Spe

Embeds and vectorize words in input corpus

Loads vectorized input training data

Shifts the content of `inputs` to the right by one so that it becomes the decoder inputs. Args: inputs: A 2d tensor with shape

r"""Decorates a function `func` as producer_func. Args: func: A function to decorate.

r""" Args: inputs: A inputs queue list to enqueue dtypes: Data types of each tensor capacity: Queue capaci