<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p></p>
<div class="moz-text-html" lang="x-unicode">
<pre style="white-space: pre-wrap; color: rgb(0, 0, 0); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">The latest version of SRILM, 1.7.3, is now available from
<a href="http://www.speech.sri.com/projects/srilm/download.html" moz-do-not-send="true">http://www.speech.sri.com/projects/srilm/download.html</a>
A list of changes appears below
Functionality
</pre>
<ul>
<li>Added nbest-oov-counts script to generate OOV counts for nbest hypotheses.</li><li>Added a simple mechanism for weight tying in nbest-rover control files. A system weight of = indicates that it should be tied to the previously listed system. This is useful for reducing the number of free parameters when searching for good system combinations
(search-rover-combo). </li><li>Add Map_noKey() and Map_noKeyP() for unsigned long long type, to enable use with size_t on Windows MSVC.</li><li>Output from -version now includes compile-time options.</li><li>Added option ngram -minbackoff to fix up models that have unnormalized probabilities or that are not smoothed.</li><li>Added option ngram -unk-probs to override unknown word probabilities.</li><li>Added nbest-optimize-args-from-rover-control script, convenient for extracting initialization parameters for nbest-optimize from existing nbest-rover control file.</li><li>Added ngram-count -text-has-weights-last option to allow text input with count values at ends of lines.</li><li>Added nbest-rover -missing-nbest option to treat missing nbest lists as if an empty hypothesis (no words) had been output, rather than simply skipping that nbest list.</li><li>Added nbest-lattice -time-penalty option, implementing a soft constraint on time stamps (when present) during confusion network building and alignment.</li><li>Added nbest-lattice -average-times option, to average word times instead of picking the timing of the highest posterior hypothesis.</li><li>Added nbest-lattice -suppress-vocab option to disallow certain words in posterior decoding.</li><li>New scripts concat-sausages for chaining word confusion networks together.</li><li>Added nbest-lattice -dump-lattice-alignments option to output mappings between sausage positions and alignment costs.</li><li>Updated Android build for 64-bit development for armv8 using NDK r20 and clang. This almost certainly breaks the 32-bit build for armv7. The last known good 32-bit build is in common/Makefile.core.android.r11c, last built using NDK r11c. To use this, copy
Makefile.core.android.r11c to Makefile.core.android. See doc/README.android.</li></ul>
<pre style="white-space: pre-wrap; color: rgb(0, 0, 0); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">Bug fixes:
</pre>
<ul>
<li>Added a new tool nbest-rover-helper that combines the functions of the combine-acoustic-scores and nbest-posteriors scripts, doing these computations in double precision and faster. nbest-rover now uses this tool (except when certain options like -nbest-backtrace
are used).</li><li>nbest-rover strips DOS end-of-line CR characters from the control file, so they no longer mess up the parsing of the file.</li><li>Rationalize the way ties are broken when decoding word confusion networks. The word with the lowest internal index is now preferred (and the *DELETEtoken always comes before all other words), unless the new nbest-lattice option -random-tie-break is given.
The output order of alternative word hypotheses to sausage files is always by probability rank first, then by internal index.</li><li>The reverse-ngram-counts script now replaces <s> with </s> and vice-versa, as required for training reverse-direction LMs, and consistent with reverse-text.</li><li>Handle comment lines starting with '##' and empty lines in nbest-rover control files the same way as in File::getline(), i.e., ignore them.</li><li>Fixed the syntax for the nbest-optimize -dynamic-random-series options (now starts with single dash, as described in man page).</li><li>Don't let compute-best-mix complain about word mismatches if <unk> is involved.</li><li>Cast input to isspace() to (unsigned char) to guarantee input is non-negative.</li><li>Fixed memory management problems in MEModel.</li><li>Work around a bug in zlib's gzprintf() printing of very long %s arguments; was causing long word strings not to be output into .gz files.</li><li>Removed word string length limit.</li><li>Removed limit on total line length in outputting ngram count files.</li><li>Zlib updated to version 1.2.11.</li><li>nbest-posteriors ensures that bytelog scores are output in fixed-point format.</li><li>Allow floating point values when parsing bytelog scores in nbest lists.</li><li>Most robustness to word sausages input files that have missing data for some position.</li><li>Fixed a performance bug when nbest-rover is invoked with -output-ctm option.</li></ul>
</div>
</body>
</html>