- make binary N-gram from ARPA N-gram file
mkbingram [-nlr forward_ngram.arpa]
[-nrl backward_ngram.arpa] [-d old_bingram_file]
is a tool to convert N-gram definition file(s) in ARPA standard
format to a compact Julius binary format. It will speed up the initial loading
time of N-gram much faster. It can read gzipped file directly.
From rev.4.0, Julius can deal with forward N-gram, backward N-gram and their
combinations. So, mkbingram
now generates binary N-gram file from one
of them, or combining them two to produce one binary N-gram.
When only a forward N-gram is specified, mkbingram
N-gram from only the forward N-gram. When using this binary N-gram at Julius,
it performs the 1st pass with the 2-gram probabilities in the N-gram, and run
the 2nd pass with the given N-gram fully, with converting forward
probabilities to backward probabilities by Bayes rule.
When only a backward N-gram is specified, mkbingram
generates an binary
N-gram file that contains only the backward N-gram. The 1st pass will use
forward 2-gram probabilities that can be computed from the backward 2-gram
using Bayes rule, and the 2nd pass use the given backward N-gram fully.
When both forward and backward N-grams are specified, the 2-gram part in the
forward N-gram and all backward N-gram will be combined into single bingram
file. The forward 2-gram will be applied for the 1st pass and backward N-gram
for the 2nd pass. Note that both N-gram should be trained in the same corpus
with same parameters (i.e. cut-off thresholds), with same vocabulary.
The old binary N-gram produced by mkbingram
of version 3.x and earlier
can be used in Julius-4, but you can convert the old version to the new
version by specifying it as input of current mkbingram
by option "
Please note that binary N-gram file converted by mkbingram
of version 4.0
and later cannot be read by older Julius 3.x.
Read in a forward (left-to-right) word N-gram file in
ARPA standard format.
Read in a backward (right-to-left) word N-gram file in
ARPA standard format.
Read in a binary N-gram file.
Swap BOS word <s> and EOS word </s> in
binary N-gram file name to output.
Convert a set of forward and backward N-gram in ARPA format into Julius binary
Convert a single forward 4-gram in ARPA format into a binary file:
Convert old binary N-gram file to current format:
( 1 ) , mkbinhmm
( 1 ) , mkbinhmmlist
( 1 )
Copyright (c) 1997-2000 Information-technology Promotion Agency, Japan
Copyright (c) 1991-2008 Kawahara Lab., Kyoto University
Copyright (c) 2000-2005 Shikano Lab., Nara Institute of Science and Technology
Copyright (c) 2005-2008 Julius project team, Nagoya Institute of Technology
The same as Julius.