Return an ordered list of indices. Batches will be constructed based on this order.

r"""Applies each `module` in :attr:`modules` in parallel on arguments contained in :attr:`inputs` (positional) and :attr:`kwargs_tup` (keyword)

Reduces output according to the training mode. Separates loss from logging and tqdm metrics :param output: :return:

remove empty lines

Remove weight normalization module from all of the layers.

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

Sanity check a few things before starting actual training. :param model:

shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir

shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir

Step-by-step decoding

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

Strip ids_to_strip from the end ids.

Ensures that segments without voice in the waveform remain no longer than a threshold determined by the VAD parameters in params.py. :par

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Initialize STFT loss module.

Initialize CausalConv1d module.

Initialization. INPUT: - in_features: shape of the input - alpha: trainable parameter alpha is in

x: [b, h, l, l] ret: [b, h, l, 2*l-1]

Saves a checkpoint atomically, avoiding the creation of incomplete checkpoints. This will create a temporary checkpoint with a suffix of ``.p

Bias for self-attention to encourage attention to close positions. Args: length: an integer scalar. Returns: a Ten

_double_threshold Computes a double threshold over the input array :param x: input array, needs to be 1d :param high_thres: High threshol

r""" Recursively find all tensors contained in the specified object.

r"""Load preprocessed audio and return a audio embeddings

r"""Load preprocessed audio and return a audio embeddings

Only supports IntervalTier currently

r"""Load preprocessed text and return text embeddings

r"""Load preprocessed text and return text embeddings

Load vocab from a file. Args: filename: The file to load vocabulary from.