<sect1 id='wfst-build-manual'> <title><command>wfst_build</command> <emphasis>Build a weighted finite-state transducer</emphasis></title> <toc depth='1'></toc> <para> </para> <sect2> <title>Synopsis</title> <para> </para> <!-- /amd/projects/festival/versions/v_mpiro/speech_tools_linux/bin/wfst_build -sgml_synopsis --> <para> <cmdsynopsis><command>wfst_build</command>[option] [rulefile0] [rulefile1] ...<arg>-type <replaceable>string</replaceable> " {kk}"</arg> <arg>-determinize </arg> <arg>-detmin </arg> <arg>-o <replaceable>ofile</replaceable></arg> <arg>-heap <replaceable>int</replaceable> " {210000}"</arg> <arg>-q </arg> </cmdsynopsis> </para> <!-- DONE /amd/projects/festival/versions/v_mpiro/speech_tools_linux/bin/wfst_build -sgml_synopsis --> <para> Build and.or process weighted finite state transducers (WFSTs) form various input formats. This program accepts descriptions in the following formats and converts them to WFSTs <itemizedlist> <listitem><para>regular expressions</para></listitem> <listitem><para>regular grammars</para></listitem> <listitem><para>Koskenniemi/Kay/Kaplan context restriction rules</para></listitem> </itemizedlist> In addition various operations can be performed on two WFSTs <itemizedlist> <listitem><para>compose: form new WFST feeding output of first WFSTs into second WFSTs.</para></listitem> <listitem><para>union: form new WFST accepting the language both WFSTs </para></listitem> <listitem><para>intersect: form new WFST accepting only the language common to both WFSTs </para></listitem> <listitem><para>concat: form new WFST accepting the language from the concatenation of all strings in the first WFST to all strings in the second. </para></listitem> </itemizedlist> The newly formed WFSTs can be optionally determinized and minimzed. The option asis allows a single WFSTs to be loaded and determinized and/or minimized </para> </sect2> <sect2> <title>OPTIONS</title> <para> </para> <!-- /amd/projects/festival/versions/v_mpiro/speech_tools_linux/bin/wfst_build -sgml_options --> <para> <variablelist> <varlistentry><term>-type</term> <LISTITEM><PARA> <replaceable>string</replaceable> " {kk}" Input rule type: kk, lts, rg, compose, regex union, intersect, concat, asis </PARA></LISTITEM> </varlistentry> <varlistentry><term>-determinize</term> <LISTITEM><PARA> Determinize WFST before saving it </PARA></LISTITEM> </varlistentry> <varlistentry><term>-detmin</term> <LISTITEM><PARA> Determinize and minimize WFST before saving it </PARA></LISTITEM> </varlistentry> <varlistentry><term>-o</term> <LISTITEM><PARA> <replaceable>ofile</replaceable> Output file for saved WFST (default stdout) </PARA></LISTITEM> </varlistentry> <varlistentry><term>-heap</term> <LISTITEM><PARA> <replaceable>int</replaceable> " {210000}" Set size of Lisp heap, needed for large rulesets </PARA></LISTITEM> </varlistentry> <varlistentry><term>-q</term> <LISTITEM><PARA> Quiet mode, no summary generated </PARA></LISTITEM> </varlistentry> </variablelist> </para> <!-- DONE /amd/projects/festival/versions/v_mpiro/speech_tools_linux/bin/wfst_build -sgml_options --> </sect2> </sect1>