BatchedXvectorComputerOptions Struct Reference
Collaboration diagram for BatchedXvectorComputerOptions:

Public Member Functions

void Register (OptionsItf *po)

Public Attributes

int32 chunk_size { 150 }
int32 batch_size { 32 }
bool pad_input { true }
NnetComputeOptions compute_config
NnetOptimizeOptions optimize_config
CachingOptimizingCompilerOptions compiler_config

Detailed Description

Definition at line 34 of file

Member Function Documentation

◆ Register()

void Register ( OptionsItf po)

Definition at line 43 of file

References BatchedXvectorComputerOptions::batch_size, BatchedXvectorComputerOptions::chunk_size, BatchedXvectorComputerOptions::pad_input, OptionsItf::Register(), NnetComputeOptions::Register(), NnetOptimizeOptions::Register(), and CachingOptimizingCompilerOptions::Register().

Referenced by main().

43  {
44  po->Register("chunk-size", &chunk_size,
45  "Size of chunk, in input frames. Includes the nnet "
46  "context, so the number of chunks will be more than "
47  "total-input-frames / chunk-size.");
48  po->Register("batch-size", &batch_size,
49  "Size of the batches of chunks that we compute at once. ");
50  po->Register("pad-input", &pad_input,
51  "If true, for utterances shorter than `chunk-size` frames "
52  "we will pad with repeats of the last frame.");
56  }
void Register(OptionsItf *opts)
Definition: nnet-optimize.h:84
virtual void Register(const std::string &name, bool *ptr, const std::string &doc)=0
void Register(OptionsItf *opts)
Definition: nnet-compute.h:42

Member Data Documentation

◆ batch_size

◆ chunk_size

◆ compiler_config

◆ compute_config

NnetComputeOptions compute_config

◆ optimize_config

◆ pad_input

The documentation for this struct was generated from the following file: