RunAll.pl Crash step 05

[Nicoeclair]

Hi,

I'm making a acoustic model but that fail during the step 05 Vector Quantize.
The exe file kmeans_init seems to crash. MSVS provides a debugger which open
on the file "_file.c". I tried to recompile several times sphinxbase and
sphinxtrain without result.

kmeans_init.exe crash when it go out of this function:

void __cdecl _lock_file (
        FILE *pf
        )
{
        /*
         * The way the FILE (pointed to by pf) is locked depends on whether
         * it is part of _iob[] or not
         */
        if ( (pf >= _iob) && (pf <= (&_iob[_IOB_ENTRIES-1])) )
        {
            /*
             * FILE lies in _iob[] so the lock lies in _locktable[].
             */
            _lock( _STREAM_LOCKS + (int)(pf - _iob) );
            /* We set _IOLOCKED to indicate we locked the stream */
            pf->_flag |= _IOLOCKED;
        }
        else
            /*
             * Not part of _iob[]. Therefore, *pf is a _FILEX and the
             * lock field of the struct is an initialized critical
             * section.
             */
            EnterCriticalSection( &(((_FILEX *)pf)->lock) );
}

OS: Windows XP (I don't use Cygwin)
Compiled with MSVS C++ 2010
Sphinx:
pocketSphinx 0.7
sphinxbase 0.7
sphinxtrain 1.0.7

MODULE: 00 verify training files
O.S. is case insensitive ("A" == "a").
Phones will be treated as case insensitive.
    Phase 1: DICT - Checking to see if the dict and filler dict agrees with the
phonelist file.
        Found 14 words using 22 phones
    Phase 2: DICT - Checking to make sure there are not duplicate entries in the
 dictionary
    Phase 3: CTL - Check general format; utterance length (must be positive); fi
les exist
    Phase 4: CTL - Checking number of lines in the transcript should match lines
 in control file
    Phase 5: CTL - Determine amount of training data, see if n_tied_states seems
 reasonable.
        Estimated Total Hours Training: 0.0231888888888889
        This is a small amount of data, no comment at this time
    Phase 6: TRANSCRIPT - Checking that all the words in the transcript are in t
he dictionary
        Words in dictionary: 11
        Words in filler dictionary: 3
    Phase 7: TRANSCRIPT - Checking that all the phones in the transcript are in
the phonelist, and all phones in the phonelist appear at least once
Feature type is s2_4x which is 4 streams
LDA/MLLT only has sense for single stream features, for example 1s_c_d_dd
Skipping LDA training
Feature type is s2_4x which is 4 streams
LDA/MLLT only has sense for single stream features, for example 1s_c_d_dd
Skipping MLLT training
MODULE: 05 Vector Quantization
<<crash here ; the script do not ends here>>
MODULE: 10 Training Context Independent models for forced alignment and VTLN
Skipped:  $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
Skipped:  $ST::CFG_VTLN set to 'no' in sphinx_train.cfg
MODULE: 11 Force-aligning transcripts
Skipped:  $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
MODULE: 12 Force-aligning data for VTLN
Skipped:  $ST::CFG_VTLN set to 'no' in sphinx_train.cfg
MODULE: 20 Training Context Independent models
    Phase 1: Cleaning up directories:
        accumulator...logs...qmanager...models...
    Phase 2: Flat initialize
<<crash again here _CrtIsValidHeapPointer(pUserData) in mk_mdef_geb.exe (no help from MSVS debugger)>>
    Phase 3: Forward-Backward
        Baum welch starting for 1 Gaussian(s), iteration: 1 (1 of 1)
Waiting for E:/Documents and Settings/T0133606/Mes documents/TÚlÚchargements/sph
inx/essai/model_parameters/essai.ci_semi_flatinitial/mixture_weights
Waiting for E:/Documents and Settings/T0133606/Mes documents/TÚlÚchargements/sph
inx/essai/model_parameters/essai.ci_semi_flatinitial/mixture_weights
Waiting for E:/Documents and Settings/T0133606/Mes documents/TÚlÚchargements/sph
inx/essai/model_parameters/essai.ci_semi_flatinitial/mixture_weights
Waiting for E:/Documents and Settings/T0133606/Mes documents/TÚlÚchargements/sph
inx/essai/model_parameters/essai.ci_semi_flatinitial/mixture_weights
<<endless loop surely due to the others bugs>>
Terminating on signal SIGINT(2)
Terminating on signal SIGINT(2)
Terminating on signal SIGINT(2)

There is no information in the logdir, essai.kmeans.log:

INFO: cmd_ln.c(691): Parsing command line:
E:\Documents and Settings\T0133606\Mes documents\Téléchargements\sphinx\essai\bin\kmeans_init.exe \
    -gthobj single \
    -stride 1 \
    -ntrial 1 \
    -minratio 0.001 \
    -ndensity 8 \
    -meanfn E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/model_parameters/essai.ci_semi_flatinitial/means \
    -varfn E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/model_parameters/essai.ci_semi_flatinitial/variances \
    -fullvar no \
    -reest no \
    -segdmpdirs E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/bwaccumdir/essai_buff_1 \
    -segdmpfn E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/bwaccumdir/essai_buff_1/essai.dmp \
    -ceplen 13 \
    -feat s2_4x \
    -agc none \
    -cmn current \
    -varnorm no

Current configuration:
[NAME]      [DEFLT]     [VALUE]
-agc        none        none
-agcthresh  2.0     2.000000e+000
-cbcntfn            
-cepdir             
-cepext     .mfc        .mfc
-ceplen     13      13
-cmn        current     current
-cmninit    8.0     8.0
-ctlfn              
-dictfn             
-dmoddeffn          
-example    no      no
-fdictfn            
-feat       1s_c_d_dd   s2_4x
-featsel            0
-fpcachesz  3000        3000
-fullvar    no      no
-gthobj     state       single
-help       no      no
-lda                
-ldadim     0       0
-lsnfn              
-maxcbobs           0
-maxiter    100     100
-maxtotobs          0
-meanfn             E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/model_parameters/essai.ci_semi_flatinitial/means
-method     rkm     rkm
-minratio   0.01        1.000000e-003
-mixwfn             
-ndensity           8
-niter      20      20
-ntrial     5       1
-obscachesz 92      92
-omoddeffn          
-reest      yes     no
-runlen             0
-segdir             
-segdmpdirs         E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/bwaccumdir/essai_buff_1,
-segdmpfn           E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/bwaccumdir/essai_buff_1/essai.dmp
-segext     v8_seg      v8_seg
-segidxfn           
-stride     32      1
-svspec             
-ts2cbfn            
-tscnt              0
-tsoff      0       0
-tsrngfn            
-varfn              E:/Documents and Settings/T0133606/Mes documents/Téléchargements/sphinx/essai/model_parameters/essai.ci_semi_flatinitial/variances
-varnorm    no      no
-vartiethr  0       0

INFO: feat.c(684): Initializing feature stream to type: 's2_4x', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: main.c(519): No mdef files.  Assuming 1-class init
INFO: main.c(1351): 1-class dump file
Fri Apr 20 09:09:38 2012

Any help is welcome

Nicoeclair

[Nickolay V. Shmyrev]

This bug was fixed in latest sources. Please download and try the snapshot of
both sphinxbase and sphinxtrain. Please see also:

http://cmusphinx.sourceforge.net/wiki/faq#qpocketsphinx_crashes_on_windows_in
_lock_file

[Nicoeclair]

Thanks for your reply

I don't know how to use this command : sphinxtrain -t an4 setup
There is no file named sphinxtrain.
Is python needed to run it ?

[Nickolay V. Shmyrev]

I don't know how to use this command : sphinxtrain -t an4 setup

Windows training is not supported in the development version. You still need
to use 1.0.7 scripts, only the binaries must be replaced.

[Nicoeclair]

Thanks : )