Construct an EncoderLayer object.

Construct an PositionalEncoding object.

Construct ConformerEncoder Args: input_size to use_dynamic_chunk, see in BaseEncoder positionwise_conv_kernel_size (i

Return the number of batches in the dataset

Numbers alone cannot accurately identify language. Because numbers are universal in all languages. So it won't be executed

The index for the first timestep. It should be set from pipeline with `set_begin_index` method.

The index for the first timestep. It should be set from pipeline with `set_begin_index` method.

The index for the first timestep. It should be set from pipeline with `set_begin_index` method.

Sets the attention processor to use [feed forward chunking](https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers).

Compute convolution module. Args: x (torch.Tensor): Input tensor (#batch, time, channels). mask_pad (torch.Tensor): us

Forward function. Args: xs: input tensor (B, L, D) Returns: output tensor, (B, L, D)

Return Swish activation function.

Compute scaled dot product attention. Args: query (torch.Tensor): Query tensor (#batch, time1, size). key (torch.Tens

Compute 'Scaled Dot Product Attention' with rel. positional encoding. Args: query (torch.Tensor): Query tensor (#batch, time1, siz

Compute encoded features. Args: x (torch.Tensor): (#batch, time, size) mask (torch.Tensor): Mask tensor for the input

Add positional encoding. Args: x (torch.Tensor): Input tensor (batch, time, `*`). Returns: torch.Tensor: Enc

Input x. Args: x (torch.Tensor): Input tensor (#batch, time, idim). x_mask (torch.Tensor): Input mask (#batch, 1, tim

Embed positions in tensor. Args: xs: padded input tensor (B, T, D) xs_lens: input length (B) decoding_chu