extend-transform-dim.cc File Reference

#include "base/kaldi-common.h"
#include "util/common-utils.h"
#include "matrix/kaldi-matrix.h"
#include "transform/transform-common.h"

Include dependency graph for extend-transform-dim.cc:

Go to the source code of this file.

Namespaces
	kaldi
	This code computes Goodness of Pronunciation (GOP) and extracts phone-level pronunciation feature for mispronunciations detection tasks, the reference:

Functions
void	IncreaseTransformDimension (int32 new_dimension, Matrix< BaseFloat > *mat)
int	main (int argc, char *argv[])

Function Documentation

main()

int main	(	int	argc,
		char *	argv[]
	)

Definition at line 54 of file extend-transform-dim.cc.

References kaldi::ClassifyRspecifier(), kaldi::ClassifyWspecifier(), SequentialTableReader< Holder >::Done(), ParseOptions::GetArg(), kaldi::IncreaseTransformDimension(), KALDI_ERR, KALDI_LOG, SequentialTableReader< Holder >::Key(), kaldi::kNoRspecifier, kaldi::kNoWspecifier, SequentialTableReader< Holder >::Next(), ParseOptions::NumArgs(), MatrixBase< Real >::NumRows(), ParseOptions::PrintUsage(), ParseOptions::Read(), kaldi::ReadKaldiObject(), ParseOptions::Register(), SequentialTableReader< Holder >::Value(), TableWriter< Holder >::Write(), and kaldi::WriteKaldiObject().

                                 {
  try {
    using namespace kaldi;

    const char *usage =
        "Read in transform from dimension d -> d (affine or linear), and output a transform\n"
        "from dimension e -> e (with e >= d, and e controlled by option --new-dimension).\n"
        "This new transform will leave the extra dimension unaffected, and transform the old\n"
        "dimensions in the same way.\n"
        "Usage: extend-transform-dim [options] (transform-A-rspecifier|transform-A-rxfilename) (transform-out-wspecifier|transform-out-wxfilename)\n"
        "E.g.: extend-transform-dim --new-dimension=117 in.mat big.mat\n";
    
    bool binary = true;
    int32 new_dimension = -1;
    ParseOptions po(usage);

    po.Register("binary", &binary, "Write in binary mode (only relevant if output is a wxfilename)");
    po.Register("new-dimension", &new_dimension,
                "Larger dimension we are changing matrix to");
    
    po.Read(argc, argv);

    if (po.NumArgs() != 2) {
      po.PrintUsage();
      exit(1);
    }

    std::string transform_in_fn = po.GetArg(1);
    std::string transform_out_fn = po.GetArg(2);
    // all these "fn"'s are either rspecifiers or filenames.

    bool in_is_rspecifier =
        (ClassifyRspecifier(transform_in_fn, NULL, NULL)
         != kNoRspecifier),
        out_is_wspecifier =
        (ClassifyWspecifier(transform_out_fn, NULL, NULL, NULL)
         != kNoWspecifier);
    
    if (in_is_rspecifier != out_is_wspecifier)
      KALDI_ERR << "Either none or both of the (input, output) must be a Table.";
    
    if (in_is_rspecifier) {
      SequentialBaseFloatMatrixReader reader(transform_in_fn);
      BaseFloatMatrixWriter writer(transform_out_fn);
      int32 num_done = 0;
      for (; !reader.Done(); reader.Next()) {
        std::string key = reader.Key();
        Matrix<BaseFloat> mat(reader.Value());
        IncreaseTransformDimension(new_dimension, &mat);
        writer.Write(key, mat);
        num_done++;
      }
      KALDI_LOG << "Increased transform dim to " << new_dimension
                << " for " << num_done << " matrices.";
      return (num_done != 0 ? 0 : 1);
    } else {
      Matrix<BaseFloat> mat;
      ReadKaldiObject(transform_in_fn, &mat);
      int32 old_dim = mat.NumRows();
      IncreaseTransformDimension(new_dimension, &mat);
      WriteKaldiObject(mat, transform_out_fn, binary);
      KALDI_LOG << "Increased transform dim from " << old_dim << " to "
                << mat.NumRows() << " and wrote to " << transform_out_fn;
      return 0;
    }
  } catch(const std::exception &e) {
    std::cerr << e.what();
    return -1;
  }
}