1 /* -*- c-basic-offset: 4; indent-tabs-mode: nil -*- */
2 /* ====================================================================
3 * Copyright (c) 1999-2007 Carnegie Mellon University. All rights
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in
15 * the documentation and/or other materials provided with the
18 * This work was supported in part by funding from the Defense Advanced
19 * Research Projects Agency and the National Science Foundation of the
20 * United States of America, and the CMU Sphinx Speech Consortium.
22 * THIS SOFTWARE IS PROVIDED BY CARNEGIE MELLON UNIVERSITY ``AS IS'' AND
23 * ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
24 * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
25 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY
26 * NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
27 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
28 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
29 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
30 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
31 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
32 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
34 * ====================================================================
38 * \file ngram_model_arpa.h ARPABO text format for N-Gram models
40 * Author: David Huggins-Daines <dhuggins@cs.cmu.edu>
43 #ifndef __NGRAM_MODEL_ARPA_H__
44 #define __NGRAM_MODEL_ARPA_H__
46 #include "ngram_model_internal.h"
47 #include "lm3g_model.h"
53 uint32 wid; /**< Index of unigram entry for this. (NOT dictionary id.) */
54 uint16 prob2; /**< Index into array of actual bigram probs */
55 uint16 bo_wt2; /**< Index into array of actual bigram backoff wts */
56 uint16 trigrams; /**< Index of 1st entry in lm_t.trigrams[],
57 RELATIVE TO its segment base (see above) */
63 * As with bigrams, trigram prob info kept in a separate table for conserving
67 uint32 wid; /**< Index of unigram entry for this. (NOT dictionary id.) */
68 uint16 prob3; /**< Index into array of actual trigram probs */
73 * Subclass of ngram_model for ARPA file reading.
75 typedef struct ngram_model_arpa_s {
76 ngram_model_t base; /**< Base ngram_model_t structure */
77 lm3g_model_t lm3g; /**< Shared lm3g structure */
79 /* Arrays of unique bigram probs and bo-wts, and trigram probs
80 * (these are temporary, actually) */
81 sorted_list_t sorted_prob2;
82 sorted_list_t sorted_bo_wt2;
83 sorted_list_t sorted_prob3;
86 #endif /* __NGRAM_MODEL_ARPA_H__ */