Return an example's size as a float or tuple. This value is used when filtering a dataset with ``--max-positions``.

load network parameters from model_dir/model_name.suffix.net :param model_dir: directory to load the model from :param suffix

Return the keys of the scp file.

Ramdom clip x to win_length. Args: x (tensor) : (B, c_in, T, n_bins). cond (tensor) : (B, T, H). x_len (te

save the network to model_dir/model_name.suffix.net :param model_dir: directory to save the model to :param suffix: suffix to

Transform a sequence of int ids into a human-readable string. EOS is not expected in ids. Args: ids: list of integers to be

Transform a human-readable string into a sequence of int ids. The ids should be in the range [num_reserved_ids, vocab_size). Ids [0,

Create a 1D, 2D, or 3D convolution module.

Parameters ---------- pattern : regex to extract pattern inc : increment of line count after extraction Retur

:param wav_data: [T] :param mel: [T, 80] :param hparams: :return:

Initialize a Linear or Convolutional layer.

Ramdom clip x to win_length. Args: x (tensor) : (B, c_in, T, n_bins). cond (tensor) : (B, T, H). x_len (te

Initialize a Linear or Convolutional layer.

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

Construct an LayerNorm object.

Create a linear module.