espnet2.asr_transducer.encoder.modules.positional_encoding.RelPositionalEncoding

source

class espnet2.asr_transducer.encoder.modules.positional_encoding.RelPositionalEncoding(size: int, dropout_rate: float = 0.0, max_len: int = 5000)

Bases: Module

Relative positional encoding.

• Parameters:
  • size – Module size.
  • max_len – Maximum input length.
  • dropout_rate – Dropout rate.

Construct a RelativePositionalEncoding object.

extend_pe(x: Tensor, left_context: int = 0) → None

Reset positional encoding.

• Parameters:
  • x – Input sequences. (B, T, ?)
  • left_context – Number of previous frames the attention module can see in current chunk.

forward(x: Tensor, left_context: int = 0) → Tensor

Compute positional encoding.

• Parameters:
  • x – Input sequences. (B, T, ?)
  • left_context – Number of previous frames the attention module can see in current chunk.
• Returns: Positional embedding sequences. (B, 2 * (T - 1), ?)
• Return type: pos_enc