espnet2.asr_transducer.encoder.modules.multi_blocks.MultiBlocks

source

class espnet2.asr_transducer.encoder.modules.multi_blocks.MultiBlocks(block_list: ~typing.List[~torch.nn.modules.module.Module], output_size: int, norm_class: ~torch.nn.modules.module.Module = <class 'torch.nn.modules.normalization.LayerNorm'>, norm_args: ~typing.Dict | None = None, blockdrop_rate: int = 0.0)

Bases: Module

MultiBlocks definition.

• Parameters:
  • block_list – Individual blocks of the encoder architecture.
  • output_size – Architecture output size.
  • norm_class – Normalization module class.
  • norm_args – Normalization module arguments.
  • blockdrop_rate – Probability threshold of dropping out each block.

Construct a MultiBlocks object.

chunk_forward(x: Tensor, pos_enc: Tensor, mask: Tensor, left_context: int = 0) → Tensor

Forward each block of the encoder architecture.

• Parameters:
  • x – MultiBlocks input sequences. (B, T, D_block_1)
  • pos_enc – Positional embedding sequences. (B, 2 * (T - 1), D_att)
  • mask – Source mask. (B, T_2)
  • left_context – Number of previous frames the attention module can see in current chunk (used by Conformer and Branchformer block).
• Returns: MultiBlocks output sequences. (B, T, D_block_N)
• Return type: x

forward(x: Tensor, pos_enc: Tensor, mask: Tensor, chunk_mask: Tensor | None = None) → Tensor

Forward each block of the encoder architecture.

• Parameters:
  • x – MultiBlocks input sequences. (B, T, D_block_1)
  • pos_enc – Positional embedding sequences.
  • mask – Source mask. (B, T)
  • chunk_mask – Chunk mask. (T_2, T_2)
• Returns: Output sequences. (B, T, D_block_N)
• Return type: x

reset_streaming_cache(left_context: int, device: device) → None

Initialize/Reset encoder streaming cache.

• Parameters:
  • left_context – Number of previous frames the attention module can see in current chunk (used by Conformer and Branchformer block).
  • device – Device to use for cache tensor.