Inference duration. Args: xs (Tensor): Batch of input sequences (B, Tmax, idim). x_masks (ByteTensor, optional): Ba

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

Perform padding for the list of tensors. Args: xs (List): List of Tensors [(T_1, `*`), (T_2, `*`), ..., (T_B, `*`)]. pad_value

Restore trainer state. Model will get its change to update :param checkpoint: :return:

To restore weights we have two cases. First, attempt to restore hpc weights. If successful, don't restore other weights.

Handle forward for each training case (distributed, single gpu, etc...) :param batch: :param batch_idx: :return:

Construct an LayerNorm object.

Initilize duration predictor module. Args: idim (int): Input dimension. n_layers (int, optional): Number of convolu

Initilize duration predictor loss module. Args: offset (float, optional): Offset value to avoid nan in log domain.

Initilize length regulator module. Args: pad_value (float, optional): Value used for padding.