 
    VoxForge
Hey Guys
I'm trying to train the german acoustic model by using the mfc files under this link
http://www.voxforge.org/de/downloads
When I use the RunAll.pl Script it goes until Mudule 20 / Phase 2: Flat initialize
---------------------------------------------------------------------------------------------------
johannes@joker-hpi:~/tutorial4/voxforge_de_sphinx$ 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 3019 words using 41 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: 0.0112428418803419
        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: 3016
        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 '' 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 '' in sphinx_train.cfg
MODULE: 20 Training Context Independent models
    Phase 1: Cleaning up directories:
        accumulator...logs...qmanager...models...
    Phase 2: Flat initialize
------------------------------------------------------------------------------------------------
After quite al long time it tells me
---------
FATAL_ERROR: "corpus.c", line 1657: Failed to get the files after 100 retries of getting MFCC(about 300 seconds)
This step had 101 ERROR messages and 0 WARNING messages.  Please check the log file for details.
Something failed: (/home/johannes/tutorial4/voxforge_de_sphinx/scripts_pl/20.ci_hmm/slave_convg.pl)
-----------
The log tells me this:
------------------------------------------------------------------------------------------------
/home/johannes/tutorial4/voxforge_de_sphinx/bin/init_gau \
 -ctlfn /home/johannes/tutorial4/voxforge_de_sphinx/etc/voxforge_de_sphinx_train.fileids \
 -part 1 \
 -npart 1 \
 -cepdir /home/johannes/tutorial4/voxforge_de_sphinx/feat \
 -cepext mfc \
 -accumdir /home/johannes/tutorial4/voxforge_de_sphinx/bwaccumdir/voxforge_de_sphinx_buff_1 \
 -agc max \
 -cmn current \
 -varnorm no \
 -feat 1s_c_d_dd \
 -ceplen 13 \
 -cepwin 0
[Switch]  [Default] [Value]
-help     no        no     
-example  no        no     
-moddeffn                  
-ts2cbfn                   
-accumdir           /home/johannes/tutorial4/voxforge_de_sphinx/bwaccumdir/voxforge_de_sphinx_buff_1
-meanfn                    
-fullvar  no        no     
-ctlfn              /home/johannes/tutorial4/voxforge_de_sphinx/etc/voxforge_de_sphinx_train.fileids
-nskip                     
-runlen                    
-part               1      
-npart              1      
-lsnfn                     
-dictfn                    
-fdictfn                   
-segdir                    
-segext   v8_seg    v8_seg 
-scaleseg no        no     
-cepdir             /home/johannes/tutorial4/voxforge_de_sphinx/feat
-cepext   mfc       mfc    
-silcomp  none      none   
-cmn      current   current
-varnorm  no        no     
-agc      max       max    
-feat     1s_c_d_dd 1s_c_d_dd
-svspec                    
-ceplen   13        13     
-cepwin   0         0      
-ldafn                     
-ldadim   29        29     
INFO: corpus.c(1343): Will process all remaining utts starting at 0
INFO: init_gau.c(146): Computing 1x1x1 mean estimates
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
Header size field: 771817472(2e010000); filesize: 15718(00003d66)
ERROR: "corpus.c", line 1653: MFCC read of de4-05 failed.  Retrying after sleep...
------------------------------------------------------------------------------------------------
and so on ....
Can anybody explain me what the problem is and how I can solve it?
I would really appreciate it.
Johannes
--- (Edited on 8/27/2009 9:23 am [GMT-0500] by JoKer) ---
The distributed MFC files are made by HTK for HTK. To train sphinx model you need to extract MFC files with:
./scripts/make_feats.pl -ctl /etc/voxforge_de_sphinx_train.fileds.
Check the tutorial for more information:
http://www.speech.cs.cmu.edu/sphinx/tutorial.html
--- (Edited on 8/27/2009 10:11 am [GMT-0500] by nsh) ---
Hi my error happen when I run script RunAll.pl
Please help me
INFO: main.c(162): No lexical transcripts provided
INFO: corpus.c(1343): Will process all remaining utts starting at 0
INFO: main.c(271): Will produce FEAT dump
INFO: main.c(426): Writing frames to one file
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat/DaoDuyKhanh/50001
.mfc) failed
ERROR: "corpus.c", line 1738: MFCC read failed.  Retrying after sleep...
stat_retry(/home/tonynguyen/test/test/feat
Thanks
Tony
--- (Edited on 5/19/2010 4:01 pm [GMT-0500] by Visitor) ---
It's better to ask your question on cmusphinx forum.
Your error caused by whitespace in fileids file that's visible in the log:
DaoDuyKhanh/50001<you have space here>
Remove this space in the fileids file in etc and it will run.
--- (Edited on 5/20/2010 09:01 [GMT+0400] by nsh) ---