#ifndef CTC_BEAM_SEARCH_DECODER_H_ #define CTC_BEAM_SEARCH_DECODER_H_ #include #include #include "scorer.h" #include "output.h" #include "alphabet.h" /* CTC Beam Search Decoder * Parameters: * probs_seq: 2-D vector that each element is a vector of probabilities * over alphabet of one time step. * alphabet: The alphabet. * beam_size: The width of beam search. * cutoff_prob: Cutoff probability for pruning. * cutoff_top_n: Cutoff number for pruning. * ext_scorer: External scorer to evaluate a prefix, which consists of * n-gram language model scoring and word insertion term. * Default null, decoding the input sample without scorer. * Return: * A vector that each element is a pair of score and decoding result, * in desending order. */ std::vector ctc_beam_search_decoder( const double* probs, int time_dim, int class_dim, const Alphabet &alphabet, size_t beam_size, double cutoff_prob, size_t cutoff_top_n, Scorer *ext_scorer); /* CTC Beam Search Decoder for batch data * Parameters: * probs_seq: 3-D vector that each element is a 2-D vector that can be used * by ctc_beam_search_decoder(). * alphabet: The alphabet. * beam_size: The width of beam search. * num_processes: Number of threads for beam search. * cutoff_prob: Cutoff probability for pruning. * cutoff_top_n: Cutoff number for pruning. * ext_scorer: External scorer to evaluate a prefix, which consists of * n-gram language model scoring and word insertion term. * Default null, decoding the input sample without scorer. * Return: * A 2-D vector that each element is a vector of beam search decoding * result for one audio sample. */ std::vector> ctc_beam_search_decoder_batch( const double* probs, int batch_size, int time_dim, int class_dim, const int* seq_lengths, int seq_lengths_size, const Alphabet &alphabet, size_t beam_size, size_t num_processes, double cutoff_prob, size_t cutoff_top_n, Scorer *ext_scorer); #endif // CTC_BEAM_SEARCH_DECODER_H_