espnet2.asr.transducer.rnnt_multi_blank.utils.cpu_utils.cpu_rnnt.CpuRNNT_metadata

source

class espnet2.asr.transducer.rnnt_multi_blank.utils.cpu_utils.cpu_rnnt.CpuRNNT_metadata(T: int, U: int, workspace: Tensor, bytes_used: int, blank: int, labels: Tensor, log_probs: Tensor, idx: CpuRNNT_index)

Bases: object

Metadata for CPU based RNNT loss calculation. Holds the working space memory.

• Parameters:
  • T – Length of the acoustic sequence (without padding).
  • U – Length of the target sequence (without padding).
  • workspace – Working space memory for the CPU.
  • bytes_used – Number of bytes currently used for indexing the working space memory. Generally 0.
  • blank – Index of the blank token in the vocabulary.
  • labels – Ground truth padded labels matrix of shape [B, U]
  • log_probs – Log probs / activation matrix of flattented shape [B, T, U, V+1]
  • idx

setup_probs(T: int, U: int, labels: Tensor, blank: int, log_probs: Tensor, idx: CpuRNNT_index)