_summary_ Args: kv_cache (bool, optional): _description_. Defaults to True. use_deepspeed (bool, optional): _descript

For getting encoding in a streaming fashion Attention!!!!! we apply dropout only once at the whole utterance level in a none

Compute relative positional encoding. Args: x (torch.Tensor): Input tensor (batch, head, time1, 2*time1-1). time1 mea

Implementation of sinc, i.e. sin(pi * x) / (pi * x) __Warning__: Different to julius.sinc, the input is multiplied by `pi`!

Implementation of sinc, i.e. sin(pi * x) / (pi * x) __Warning__: Different to julius.sinc, the input is multiplied by `pi`!

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

Args: audio(torch.Tensor): shape (1, t) Returns: mel(torch.Tensor): shape (1, num_mels, t')

Initialization. INPUT: - in_features: shape of the input - alpha - trainable parameter that controls frequenc

Multi-Head Attention layer with relative position encoding. Paper: https://arxiv.org/abs/1901.02860 Args: n_head (int): Th

Construct an PositionalEncoding object.

Construct a PositionwiseFeedForward object.

Construct an linear object.

Construct an EncoderLayer object.