ERROR: "lexicon.c", line 223: pronunciation for NOVE has undefined phones; skipping.
You should check your dictionary because it's format is broken. I suppose it has some non-printed characters like carriage-return from Windows. Remove them to make things work. It's prefered to work with unix-based text editors only and avoid windows notepads since they insert carriage return inconsistently.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
this is the script baum_welch.pl log file . I'm doing a semi-continuous model. what can I do?
INFO: main.c(196): Compiled on Jun 7 2007 at 16:27:57
/home/aenima1891/tutorial/numeri/bin/bw \ -moddeffn /home/aenima1891/tutorial/numeri/model_architecture/numeri.ci.mdef \ -ts2cbfn .semi. \ -mixwfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/mixture_weights \ -mwfloor 1e-08 \ -tmatfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/transition_matrices \ -meanfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/means \ -varfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/variances \ -ltsoov no \ -dictfn /home/aenima1891/tutorial/numeri/etc/numeri.dic \ -fdictfn /home/aenima1891/tutorial/numeri/etc/numeri.filler \ -ctlfn /home/aenima1891/tutorial/numeri/etc/numeri_train.fileids \ -part 1 \ -npart 1 \ -cepdir /home/aenima1891/tutorial/numeri/feat \ -cepext mfc \ -lsnfn /home/aenima1891/tutorial/numeri/etc/numeri_train.transcription \ -accumdir /home/aenima1891/tutorial/numeri/bwaccumdir/numeri_buff_1 \ -varfloor 0.0001 \ -topn 4 \ -abeam 1e-90 \ -bbeam 1e-10 \ -agc none \ -cmn current \ -varnorm no \ -meanreest yes \ -varreest yes -2passvar no \ -tmatreest yes \ -fullvar no \ -diagfull no \ -feat c/1..L-1/,d/1..L-1/,c/0/d/0/dd/0/,dd/1..L-1/ \ -ceplen 13 \ -timing no
[Switch] [Default] [Value]
-help no no
-example no no
-hmmdir
-moddeffn /home/aenima1891/tutorial/numeri/model_architecture/numeri.ci.mdef
-tmatfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/transition_matrices
-mixwfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/mixture_weights
-meanfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/means
-varfn /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/variances
-fullvar no no
-diagfull no no
-mwfloor 0.00001 1.000000e-08
-tpfloor 0.0001 1.000000e-04
-varfloor 0.00001 1.000000e-04
-topn 4 4
-dictfn /home/aenima1891/tutorial/numeri/etc/numeri.dic
-fdictfn /home/aenima1891/tutorial/numeri/etc/numeri.filler
-ltsoov no no
-ctlfn /home/aenima1891/tutorial/numeri/etc/numeri_train.fileids
-nskip
-runlen -1 -1
-part 1
-npart 1
-cepext mfc mfc
-cepdir /home/aenima1891/tutorial/numeri/feat
-phsegext phseg phseg
-phsegdir
-outphsegdir
-sentdir
-sentext sent sent
-lsnfn /home/aenima1891/tutorial/numeri/etc/numeri_train.transcription
-accumdir /home/aenima1891/tutorial/numeri/bwaccumdir/numeri_buff_1
-ceplen 13 13
-cepwin 0 0
-agc max none
-cmn current current
-varnorm no no
-silcomp none none
-sildel no no
-siltag SIL SIL
-abeam 1e-100 1.000000e-90
-bbeam 1e-100 1.000000e-10
-varreest yes yes
-meanreest yes yes
-mixwreest yes yes
-tmatreest yes yes
-mllrmat
-cb2mllrfn .1cls. .1cls.
-ts2cbfn .semi.
-feat c/1..L-1/,d/1..L-1/,c/0/d/0/dd/0/,dd/1..L-1/
-ldafn
-ldadim 29 29
-ldaaccum no no
-timing yes no
-viterbi no no
-2passvar no no
-sildelfn
-spthresh 0.0 0.000000e+00
-maxuttlen 0 0
-ckptintv
-outputfullpath no no
-fullsuffixmatch no no
-pdumpdir
INFO: main.c(253): Reading /home/aenima1891/tutorial/numeri/model_architecture/numeri.ci.mdef
INFO: model_def_io.c(587): Model definition info:
INFO: model_def_io.c(588): 18 total models defined (18 base, 0 tri)
INFO: model_def_io.c(589): 108 total states
INFO: model_def_io.c(590): 90 total tied states
INFO: model_def_io.c(591): 90 total tied CI states
INFO: model_def_io.c(592): 18 total tied transition matrices
INFO: model_def_io.c(593): 6 max state/model
INFO: model_def_io.c(594): 6 min state/model
INFO: s3mixw_io.c(116): Read /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/mixture_weights [90x4x256 array]
WARNING: "mod_inv.c", line 368: Model inventory n_density not set; setting to value in mixw file, 256.
INFO: s3tmat_io.c(115): Read /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/transition_matrices [18x5x6 array]
INFO: mod_inv.c(296): inserting tprob floor 1.000000e-04 and renormalizing
INFO: s3gau_io.c(166): Read /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/means [1x4x256 array]
INFO: s3gau_io.c(166): Read /home/aenima1891/tutorial/numeri/model_parameters/numeri.ci_semi_flatinitial/variances [1x4x256 array]
INFO: gauden.c(183): 1 total mgau
INFO: gauden.c(155): 4 feature streams (|0|=12 |1|=24 |2|=3 |3|=12 )
INFO: gauden.c(194): 256 total densities
INFO: gauden.c(98): min_var=1.000000e-04
INFO: gauden.c(172): compute 4 densities/frame
INFO: main.c(361): Will reestimate mixing weights.
INFO: main.c(363): Will reestimate means.
INFO: main.c(365): Will reestimate variances.
INFO: main.c(367): WIll NOT optionally delete silence in Baum Welch or Viterbi.
INFO: main.c(375): Will reestimate transition matrices
INFO: main.c(388): Reading main lexicon: /home/aenima1891/tutorial/numeri/etc/numeri.dic
ERROR: "acmod_set.c", line 447: Error parsing acoustic model name
ERROR: "lexicon.c", line 96: Unknown phone
ERROR: "lexicon.c", line 223: pronunciation for NOVE has undefined phones; skipping.
ERROR: "acmod_set.c", line 447: Error parsing acoustic model name
ERROR: "lexicon.c", line 96: Unknown phone
Mon Jun 11 15:41:38 2007
You should check your dictionary because it's format is broken. I suppose it has some non-printed characters like carriage-return from Windows. Remove them to make things work. It's prefered to work with unix-based text editors only and avoid windows notepads since they insert carriage return inconsistently.