Blame view
src/gmmbin/gmm-compute-likes.cc
2.74 KB
8dcb6dfcb
first commit
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
// gmmbin/gmm-compute-likes.cc
// Copyright 2009-2011 Microsoft Corporation
// See ../../COPYING for clarification regarding multiple authors
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// THIS CODE IS PROVIDED *AS IS* BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION ANY IMPLIED
// WARRANTIES OR CONDITIONS OF TITLE, FITNESS FOR A PARTICULAR PURPOSE,
// MERCHANTABLITY OR NON-INFRINGEMENT.
// See the Apache 2 License for the specific language governing permissions and
// limitations under the License.
#include "base/kaldi-common.h"
#include "util/common-utils.h"
#include "gmm/am-diag-gmm.h"
#include "hmm/transition-model.h"
#include "fstext/fstext-lib.h"
#include "base/timer.h"
int main(int argc, char *argv[]) {
try {
using namespace kaldi;
typedef kaldi::int32 int32;
using fst::SymbolTable;
using fst::VectorFst;
using fst::StdArc;
const char *usage =
"Compute log-likelihoods from GMM-based model
"
"(outputs matrices of log-likelihoods indexed by (frame, pdf)
"
"Usage: gmm-compute-likes [options] model-in features-rspecifier likes-wspecifier
";
ParseOptions po(usage);
po.Read(argc, argv);
if (po.NumArgs() != 3) {
po.PrintUsage();
exit(1);
}
std::string model_in_filename = po.GetArg(1),
feature_rspecifier = po.GetArg(2),
loglikes_wspecifier = po.GetArg(3);
AmDiagGmm am_gmm;
{
bool binary;
TransitionModel trans_model; // not needed.
Input ki(model_in_filename, &binary);
trans_model.Read(ki.Stream(), binary);
am_gmm.Read(ki.Stream(), binary);
}
BaseFloatMatrixWriter loglikes_writer(loglikes_wspecifier);
SequentialBaseFloatMatrixReader feature_reader(feature_rspecifier);
int32 num_done = 0;
for (; !feature_reader.Done(); feature_reader.Next()) {
std::string key = feature_reader.Key();
const Matrix<BaseFloat> &features (feature_reader.Value());
Matrix<BaseFloat> loglikes(features.NumRows(), am_gmm.NumPdfs());
for (int32 i = 0; i < features.NumRows(); i++) {
for (int32 j = 0; j < am_gmm.NumPdfs(); j++) {
SubVector<BaseFloat> feat_row(features, i);
loglikes(i, j) = am_gmm.LogLikelihood(j, feat_row);
}
}
loglikes_writer.Write(key, loglikes);
num_done++;
}
KALDI_LOG << "gmm-compute-likes: computed likelihoods for " << num_done
<< " utterances.";
return 0;
} catch(const std::exception &e) {
std::cerr << e.what();
return -1;
}
}
|