21 #ifndef KALDI_NNET2_NNET_EXAMPLE_H_ 22 #define KALDI_NNET2_NNET_EXAMPLE_H_ 43 std::vector<std::vector<std::pair<int32, BaseFloat> > >
labels;
60 void Write(std::ostream &os,
bool binary)
const;
61 void Read(std::istream &is,
bool binary);
103 void AcceptExamples(std::vector<NnetExample> *examples);
113 bool ProvideExamples(std::vector<NnetExample> *examples);
175 void Write(std::ostream &os,
bool binary)
const;
176 void Read(std::istream &is,
bool binary);
191 #endif // KALDI_NNET2_NNET_EXAMPLE_H_ CompressedMatrix input_frames
The input data, with NumRows() >= labels.size() + left_context; it includes features to the left and ...
This code computes Goodness of Pronunciation (GOP) and extracts phone-level pronunciation feature for...
NnetExample is the input data and corresponding label (or labels) for one or more frames of input...
Semaphore empty_semaphore_
std::vector< NnetExample > examples_
int32 left_context
The number of frames of left context (we can work out the #frames of right context from input_frames...
SequentialTableReader< KaldiObjectHolder< NnetExample > > SequentialNnetExampleReader
void Read(std::istream &is, bool binary)
A templated class for writing objects to an archive or script file; see The Table concept...
#define KALDI_DISALLOW_COPY_AND_ASSIGN(type)
Allows random access to a collection of objects in an archive or script file; see The Table concept...
TableWriter< KaldiObjectHolder< DiscriminativeNnetExample > > DiscriminativeNnetExampleWriter
RandomAccessTableReader< KaldiObjectHolder< DiscriminativeNnetExample > > RandomAccessDiscriminativeNnetExampleReader
This class stores neural net training examples to be used in multi-threaded training.
RandomAccessTableReader< KaldiObjectHolder< NnetExample > > RandomAccessNnetExampleReader
A templated class for reading objects sequentially from an archive or script file; see The Table conc...
Vector< BaseFloat > spk_info
spk_info contains any component of the features that varies slowly or not at all with time (and hence...
CompactLattice den_lat
The denominator lattice.
SequentialTableReader< KaldiObjectHolder< DiscriminativeNnetExample > > SequentialDiscriminativeNnetExampleReader
Matrix< BaseFloat > input_frames
The input data– typically with a number of frames [NumRows()] larger than labels.size(), because it includes features to the left and right as needed for the temporal context of the network.
std::vector< int32 > num_ali
The numerator alignment.
TableWriter< KaldiObjectHolder< NnetExample > > NnetExampleWriter
BaseFloat weight
The weight we assign to this example; this will typically be one, but we include it for the sake of g...
fst::VectorFst< CompactLatticeArc > CompactLattice
int32 GetLabelSingle(int32 frame, BaseFloat *weight=NULL)
Get the maximum weight label (pdf_id and weight) of this frame of this example.
This struct is used to store the information we need for discriminative training (MMI or MPE)...
A class representing a vector.
std::vector< std::vector< std::pair< int32, BaseFloat > > > labels
The label(s) for each frame in a sequence of frames; in the normal case, this will be just [ [ (pdf-i...
Semaphore full_semaphore_
int32 left_context
The number of frames of left context in the features (we can work out the #frames of right context fr...
void SetLabelSingle(int32 frame, int32 pdf_id, BaseFloat weight=1.0)
Set the label of this frame of this example to the specified pdf_id with the specified weight...
void Write(std::ostream &os, bool binary) const
Vector< BaseFloat > spk_info
The speaker-specific input, if any, or an empty vector if we're not using this features.