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_dmp.h DMP format for N-Gram models
40 * Author: David Huggins-Daines <dhuggins@cs.cmu.edu>
43 #ifndef __NGRAM_MODEL_DMP_H__
44 #define __NGRAM_MODEL_DMP_H__
46 #include "sphinxbase/mmio.h"
48 #include "ngram_model_internal.h"
49 #include "lm3g_model.h"
52 * On-disk representation of bigrams.
55 uint16 wid; /**< Index of unigram entry for this. (NOT dictionary id.) */
56 uint16 prob2; /**< Index into array of actual bigram probs */
57 uint16 bo_wt2; /**< Index into array of actual bigram backoff wts */
58 uint16 trigrams; /**< Index of 1st entry in lm_t.trigrams[],
59 RELATIVE TO its segment base (see lm3g_model.h) */
63 * On-disk representation of trigrams.
65 * As with bigrams, trigram prob info kept in a separate table for conserving
69 uint16 wid; /**< Index of unigram entry for this. (NOT dictionary id.) */
70 uint16 prob3; /**< Index into array of actual trigram probs */
74 * Subclass of ngram_model for DMP file reading.
76 typedef struct ngram_model_dmp_s {
77 ngram_model_t base; /**< Base ngram_model_t structure */
78 lm3g_model_t lm3g; /**< Common lm3g_model_t structure */
79 mmio_file_t *dump_mmap; /**< mmap() of dump file (or NULL if none) */
83 * Construct a DMP format model from a generic base model.
85 * Note: If base is already a DMP format model, this just calls
86 * ngram_model_retain(), and any changes will also be made in the base
89 ngram_model_dmp_t *ngram_model_dmp_build(ngram_model_t *base);
92 #endif /* __NGRAM_MODEL_DMP_H__ */