espnet2.asr_transducer.encoder.encoder.Encoder

source

class espnet2.asr_transducer.encoder.encoder.Encoder(input_size: int, body_conf: List[Dict[str, Any]], input_conf: Dict[str, Any] = {}, main_conf: Dict[str, Any] = {})

Bases: Module

Encoder module definition.

• Parameters:
  • input_size – Input size.
  • body_conf – Encoder body configuration.
  • input_conf – Encoder input configuration.
  • main_conf – Encoder main configuration.

Construct an Encoder object.

chunk_forward(x: Tensor, x_len: Tensor, processed_frames: tensor, left_context: int = 32) → Tensor

Encode input sequences as chunks.

• Parameters:
  • x – Encoder input features. (1, T_in, F)
  • x_len – Encoder input features lengths. (1,)
  • processed_frames – Number of frames already seen.
  • left_context – Number of previous frames (AFTER subsampling) the attention module can see in current chunk.
• Returns: Encoder outputs. (B, T_out, D_enc)
• Return type: x

forward(x: Tensor, x_len: Tensor) → Tuple[Tensor, Tensor]

Encode input sequences.

• Parameters:
  • x – Encoder input features. (B, T_in, F)
  • x_len – Encoder input features lengths. (B,)
• Returns: Encoder outputs. (B, T_out, D_enc) x_len: Encoder outputs lenghts. (B,)
• Return type: x

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

Initialize/Reset encoder cache for streaming.

• Parameters:
  • left_context – Number of previous frames (AFTER subsampling) the attention module can see in current chunk.
  • device – Device ID.