nbest-to-lattice.cc File Reference

#include "base/kaldi-common.h"
#include "util/common-utils.h"
#include "fstext/fstext-lib.h"
#include "lat/kaldi-lattice.h"

Include dependency graph for nbest-to-lattice.cc:

Go to the source code of this file.

Functions
bool	GetUtteranceId (const std::string &nbest_id, std::string *utterance_id)
int	main (int argc, char *argv[])

Function Documentation

GetUtteranceId()

bool GetUtteranceId	(	const std::string &	nbest_id,
		std::string *	utterance_id
	)

Definition at line 27 of file nbest-to-lattice.cc.

Referenced by main().

                                                                        {
  size_t pos = nbest_id.find_last_of('-');
  if (pos == std::string::npos || pos == 0) return false;
  else{
    *utterance_id = std::string(nbest_id, 0, pos);
    return true;
  }
}

main()

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

Definition at line 36 of file nbest-to-lattice.cc.

References SequentialTableReader< Holder >::Done(), ParseOptions::GetArg(), GetUtteranceId(), KALDI_ERR, KALDI_LOG, SequentialTableReader< Holder >::Key(), SequentialTableReader< Holder >::Next(), ParseOptions::NumArgs(), ParseOptions::PrintUsage(), ParseOptions::Read(), SequentialTableReader< Holder >::Value(), and TableWriter< Holder >::Write().

                                 {
  try {
    using namespace kaldi;
    typedef kaldi::int32 int32;

    const char *usage =
        "Read in a Table containing N-best entries from a lattices (i.e. individual\n"
        "lattices with a linear structure, one for each N-best entry, indexed by\n"
        "utt_id_a-1, utt_id_a-2, etc., and take the union of them for each utterance\n"
        "id (e.g. utt_id_a), outputting a lattice for each.\n"
        "Usage:  nbest-to-lattice <nbest-rspecifier> <lattices-wspecifier>\n"
        " e.g.: nbest-to-lattice ark:1.nbest ark:1.lats\n";
      
    ParseOptions po(usage);
    
    po.Read(argc, argv);

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

    std::string nbest_rspecifier = po.GetArg(1),
        lats_wspecifier = po.GetArg(2);


    SequentialCompactLatticeReader compact_nbest_reader(nbest_rspecifier);
    CompactLatticeWriter compact_lattice_writer(lats_wspecifier); 

    int32 n_nbest_done = 0, n_utt_done = 0;

    // The variable "cur_union" will be the union of FSTs for a
    // particular utterance-id, if we have any "pending".
    CompactLattice cur_union;
    std::string cur_utt_id;

    for (; !compact_nbest_reader.Done(); compact_nbest_reader.Next()) {
      std::string nbest_id = compact_nbest_reader.Key();
      const CompactLattice &this_nbest = compact_nbest_reader.Value();
      std::string utt_id;
      if (!GetUtteranceId(nbest_id, &utt_id)) {
        KALDI_ERR << "Invalid n-best id " << nbest_id << ": make sure you "
            "are giving N-bests to nbest-to-lattice.";
      }
      if (utt_id != cur_utt_id) { // change in utterance.
        if (cur_utt_id != "") {
          compact_lattice_writer.Write(cur_utt_id, cur_union);
          cur_union.DeleteStates();
        }
        n_utt_done++; // We increment this when we start processing a
        // new utterance.
        cur_utt_id = utt_id;
      }
      Union(&cur_union, this_nbest);
      n_nbest_done++;
    }

    if (cur_utt_id != "")
      compact_lattice_writer.Write(cur_utt_id, cur_union);
    
    KALDI_LOG << "Done joining n-best into lattices for "
              << n_utt_done << " utterances, with on average "
              << (n_nbest_done/static_cast<BaseFloat>(n_utt_done))
              << " N-best paths per utterance.";
    return (n_utt_done != 0 ? 0 : 1);
  } catch(const std::exception &e) {
    std::cerr << e.what();
    return -1;
  }
}