g2p.pl -v
  g2p.pl -task apply -lng myLanguage -i myInputFile -iform myInputFormat \
         -o myOutputFile -oform myOutputFormat [-featset myFeatureSet] \
         [-syl mySyl] [-stress myStress] [-align myAlign] \
         [-map myMap] [-c myConfigFile] [-tgitem myTgItem] [-tgrate myTgRate]
	 [-ensemble myEnsemble] [-embed myEmbed]
  g2p.pl -task train -lng myLanguage -c myConfigFile [-featset myFeatureSet]
        -v: displays current version
	myTask: train,apply
	myLanguage: aus,deu,ekk,eng,fra,ita,kat,hun,nld,nze,pol,ron,slk,sqi,use
                    corresponding to iso639-3 wherever available (Exceptions:
		    aus, nze, use for Australien and New Zealand and American
		    English, resp.).
		    Alternatively rfc5646 codes are accepted (e.g. eng-GB,
		    eng-AU, eng-NZ, eng-US)
	myInputFormat: txt - plain text
	               bpf - bas partiture format
                       list - word list (different POS tagging strategy)
		       tcf - TCF format; <token> element is obligatory
		       tg  - textGrid; long and short format supported
	myOutputFormat: txt - t r a n s c r i p t i o n <tab>
                                    t r a n s c r i p ...
	                tab - word;t r a n s c r i p t i o n
			exttab - word;t r a n s c r i p t i o n;
			       	 partOfSpeech;m o r p h s;
				 m o r p h c l a s s e s
				 Currently only supported for lng=deu|eng.
	                bpf - bas partiture format
                              contains ORT and KAN tiers,
			      no blancs between phonemes
	                bpfs- bas partiture format
                              contains ORT and KAN tier,
			      blancs between phonemes
			extbpf - bas partiture format
                              contains ORT, KAN, POS, KSS, TRL, MRP tiers.
			      KSS: full transcription
			      TRL: ORT + punctuation
			      MRP: m o r p h s;m o r p h c l a s s e s
			extbpfs - bas partiture format. As bpfext with
			      blancs between phonemes
	                lex - word;t r a n s c r i p t i o n
	                      words are unique and alphanumerically sorted
			extlex - output as for exttab, but unique and sorted.
			         Currently only supported for
				 lng=aus|deu|eng|nze|use.
                        tcf - TCF format with added trancriptions
                              (for non-TCF input, elements <text> and
                              <tokens> are generated from scratch)
                        exttcf - additional output of part of speech,
                              morphs and morph classes. Currently only
			      supported for lng=aus|deu|eng|nze|use.
			tg - textGrid. If iform is tg, the same format
			     (long or short) is returned.
                             Item bas_trs will be added, that contains
			     the transcription for each interval in item myItem
			     which is to be specified in -tgitem myItem.
			     Requires iform 'tg'
			exttg - extended textGrid. If iform is tg, the same
			     format (long or short) is returned. Items
			     bas_trs, bas_pos, bas_m, and bas_mc will
			     be added that contain transcription, part of
			     speech, morphemes, and morpheme classes,
			     respectively, for each interval in item myItem
			     which is to be specified in -tgitem myItem.
			     Requires iform 'tg'. Currently only supported
			     for lng=aus|deu|eng|nze|use. 
        myFeatureset: used feature set for grapheme-phoneme conversion and
		      for word stress determination
		      <standard>
		      extended (currently only supported for lng=deu|eng)
        mySyl: syllabification yes|<no>
	myStress: word stress assignment yes|<no>
	myAlign: letter alignment of phonemes yes|<no>|maus.
		 If switched on, also the grapheme string is splitted
		 letter-wise (multi-character letters are kept). No grapheme
		 split for tcf input (original token content is kept).
	myMap: from_to (e.g. deu_eng) - maps G2P output from SAMPA inventory
             of lngX to lngY. lngY includes <sampa>, which is the MAUS general
             SAMPA inventory.
             Currently supported for:
             pol_sampa
             hun_sampa
             deu_maus (sampa subset for German MAUS, without /6/-diphtongs)
             hun_maus (sampa subset for Hungarian MAUS)
             {aus|deu|ekk|eng|fra|ita|kat|hun|nld|nze|pol|ron|slk|sqi|use}_ipa
	     use_arpabet
             instead of 3-letter language code rfc5646 code can be used,
	     e.g. eng-US_arpabet.
             REMARK: if a bpf(s) output file is to be created as MAUS input
                     set macro parameter -embed to 'maus'!
             default <no>
	myConfigFile: language-dependent default config files given.
	myTgItem: needed for iform=tg. Name of the TextGrid item from which
	     the text is to be extracted
	myTgRate: needed for the combination of iform=tg and oform=bpf(s).
	     Sample rate (in samples per second), so that time values of the
	     TextGrid can be converted to sample values in the bpf
        myEnsemble:
	     <alley>: sequential classification reducing the grapheme
                      context until mapping is found
             forest: parallel classification with maximum votes decision  
	myEmbed: <no>|maus. Macro parameter for task=apply.
	     If set to 'maus', then
	     -{syl|stress} set to 'no'  
	     -align: if not 'no', set to 'maus'
	     -map set to 'myLanguage_maus'
	     -oform: if not 'bpf(s)', set to 'bpf'

                                               Uwe Reichel, IPS, 20141006