Speech Recognition Engines

Flat
SPHINX 3: Problem with perl scripts_pl/RunAll.pl
User: dipankar
Date: 9/12/2013 12:44 am
Views: 2755
Rating: 3

Getting the following error "cmd_ln.c", line 427: Unparsed boolean value '' for 20.ci_hmm/slave_convg.pl

Output :

[root@dipankar an4]# perl scripts_pl/RunAll.pl
MODULE: 00 verify training files
O.S. is case sensitive ("A" != "a").
Phones will be treated as case sensitive.
    Phase 1: DICT - Checking to see if the dict and filler dict agrees with the phonelist file.
        Found 133 words using 34 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); files 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.
        Total Hours Training: 0.704874786324802
        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 the dictionary
        Words in dictionary: 130
        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
MODULE: 01 Train LDA transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 02 Train MLLT transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 05 Vector Quantization
Skipped for continuous models
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
    Phase 3: Forward-Backward
        Baum welch starting for 1 Gaussian(s), iteration: 1 (1 of 1)
        0%
This step had 1 ERROR messages and 0 WARNING messages.  Please check the log file for details.
0
Only 0 parts of 1 of Baum Welch were successfully completed
Parts 1 failed to run!
Training failed in iteration 1
Something failed: (/home/dipankar/sphinx/tutorial/an4/scripts_pl/20.ci_hmm/slave_convg.pl)

[root@dipankar an4]#

Log File :

 

        INFO: main.c(196): Compiled on Jul 25 2013 at 14:50:42
/home/dipankar/sphinx/tutorial/an4/bin/bw \
 -moddeffn /home/dipankar/sphinx/tutorial/sphinxbase-0.8/model_architecture/an4.ci.mdef \
 -ts2cbfn .cont. \
 -mixwfn /home/dipankar/sphinx/tutorial/sphinxbase-0.8/model_parameters/an4.ci_cont_flatinitial/mixture_weights \
 -mwfloor 1e-08 \
 -tmatfn /home/dipankar/sphinx/tutorial/sphinxbase-0.8/model_parameters/an4.ci_cont_flatinitial/transition_matrices \
 -meanfn /home/dipankar/sphinx/tutorial/sphinxbase-0.8/model_parameters/an4.ci_cont_flatinitial/means \
 -varfn /home/dipankar/sphinx/tutorial/sphinxbase-0.8/model_parameters/an4.ci_cont_flatinitial/variances \
 -ltsoov  \
 -dictfn etc/an4.dic \
 -fdictfn etc/an4.filler \
 -ctlfn etc/an4_train.fileids \
 -part 1 \
 -npart 1 \
 -cepdir /home/dipankar/sphinx/tutorial/an4/feat \
 -cepext mfc \
 -lsnfn etc/an4_train.transcription \
 -accumdir /home/dipankar/sphinx/tutorial/sphinxbase-0.8/bwaccumdir/an4_buff_1 \
 -varfloor 0.0001 \
 -topn 1 \
 -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 1s_c_d_dd \
 -ceplen 13 \
 -cepwin 0 \
 -timing no

ERROR: "cmd_ln.c", line 427: Unparsed boolean value ''
Thu Sep 12 11:05:03 2013


Not getting whats going wrong.Any help is appreciated.

 

 

--- (Edited on 9/12/2013 12:44 am [GMT-0500] by ) ---

--- (Edited on 9/12/2013 12:47 am [GMT-0500] by ) ---

--- (Edited on 9/12/2013 12:56 am [GMT-0500] by ) ---

PreviousNext