sphinxtrain runall.pl error

Speech Recognition Engines

Flat

User: kas
Date: 5/18/2010 7:06 am

Views: 10944
Rating: 1

hello t friends !!!!!!!!!

while running scripts_pl/runall.pl , i encoutered the following errors

only 0 parts of 1 of baum welch were sucessfully completed

part 1 failed to run!

training failed in iteration 1

something failed<C:/project/myproject/scripts_pl/20.ci_hmm/slave_convg.pl>

bw.exe stopeed working

please anyone help

--- (Edited on 5/18/2010 7:06 am [GMT-0500] by kas) ---

Re: sphinxtrain runall.pl error

User: nsh
Date: 5/18/2010 10:47 am

Views: 123
Rating: 1

Please provide more information about your problem. In particular you need to check the log in logdir subfolder. It usually contains more information about problem.

--- (Edited on 5/18/2010 19:47 [GMT+0400] by nsh) ---

Re: sphinxtrain runall.pl error

User: amitkr
Date: 5/25/2010 6:18 am

Views: 110
Rating: 1

hey,

i tried to run the follwing command perl RunAll.pl

but its giving

Configuration (e.g. etc/sphinx_train.cfg) not defined
Compilation failed in require at RunAll.pl line 48.
BEGIN failed--compilation aborted at RunAll.pl line 48.

--- (Edited on 5/25/2010 6:18 am [GMT-0500] by amitkr) ---

Re: sphinxtrain runall.pl error

User: nsh
Date: 5/25/2010 12:33 pm

Views: 95
Rating: 1

> i tried to run the follwing command perl RunAll.pl

It's important in which folder you are running this command. It must be training root folder, not scripts_pl folder. So the proper way would be

cd model_folder

perl ./scripts_pl/RunAll.pl

--- (Edited on 5/25/2010 21:33 [GMT+0400] by nsh) ---

Re: sphinxtrain runall.pl error

User: amitkr
Date: 5/26/2010 2:40 am

Views: 89
Rating: 1

thanks for ur help...

I tried this following command:

[bharati@Bharati-Speech SphinxTrain]$ 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 Vector Quantization
Skipped for continuous models
MODULE: 02 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: 03 Force-aligning transcripts
Skipped: $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
MODULE: 04 Force-aligning data for VTLN
Skipped: $ST::CFG_VTLN set to 'no' in sphinx_train.cfg
MODULE: 05 Train LDA transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 06 Train MLLT transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
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% FATAL_ERROR: "mod_inv.c", line 185: mean file contains a different # of Gaussian densities, 8, per mixture than previously defined, 1

Failed to start bw
Failed to copy /home/bhrati/Desktop/an4/model_architecture/an4.ci.mdef to /home/bhrati/Desktop/an4/model_parameters/an4.ci_cont/mdef: Permission denied at /home/bhrati/Desktop/an4/scripts_pl/20.ci_hmm/norm.pl line 90.
        Current Overall Likelihood Per Frame = -6.96099447339583
        Baum welch starting for 1 Gaussian(s), iteration: 2 (1 of 1)
        0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%

there is this FATAL ERROR and its not proceeding after this..

plzz help as its very imp for me and I'm new to this field so kindly explain in details...

--- (Edited on 5/26/2010 2:40 am [GMT-0500] by Visitor) ---

Re: sphinxtrain runall.pl error

User: amitkr
Date: 5/26/2010 3:21 am

Views: 55
Rating: 3

hey,

I overcame that problem but after giving the following command:

[root@Bharati-Speech an4]# perl scripts_pl/decode/slave.pl

Can't locate /home/bhrati/Desktop/an4/scripts_pl/util/utils.pl in @INC (@INC contains: /usr/local/lib/perl5/site_perl/5.10.0/i386-linux-thread-multi /usr/local/lib/perl5/site_perl/5.10.0 /usr/lib/perl5/vendor_perl/5.10.0/i386-linux-thread-multi /usr/lib/perl5/vendor_perl/5.10.0 /usr/lib/perl5/vendor_perl /usr/lib/perl5/5.10.0/i386-linux-thread-multi /usr/lib/perl5/5.10.0 /usr/lib/perl5/site_perl .) at etc/sphinx_decode.cfg line 23.
Compilation failed in require at scripts_pl/decode/slave.pl line 52.

In an4/scripts_pl directory there is no util directory..

even from sphinxtrain folder error is showing:

[root@Bharati-Speech SphinxTrain]# perl scripts_pl/decode/slave.pl

Configuration (e.g. etc/sphinx_train.cfg) not defined
Compilation failed in require at scripts_pl/decode/slave.pl line 45.
BEGIN failed--compilation aborted at scripts_pl/decode/slave.pl line 45.

in slave.pl line 45 contain :

use SphinxTrain::Util ;

In SphinxTrain/scripts_pl directory there is no util directory..

I'm using sphinxtrain 3 0.6.3.tar.gz

plzz guide me in this only...

what should i do plzz guide me.....

--- (Edited on 5/26/2010 3:21 am [GMT-0500] by amitkr) ---

--- (Edited on 5/26/2010 5:06 am [GMT-0500] by amitkr) ---

--- (Edited on 5/26/2010 5:30 am [GMT-0500] by amitkr) ---

Re: sphinxtrain runall.pl error

User: nsh
Date: 5/26/2010 5:23 am

Views: 39
Rating: 1

> In an4/scripts_pl directory there is no util directory..

You need to make sure you are using recent sphinx3 and that slave.pl script is taken from sphinxtrain scrips_pl folder. It should have

use SphinxTrain::Util;

on line 46. Make sure you follow instructions precisely.

The file Util.pm should be located in scripts_pl/lib/SphinxTrain/Util.pm

> even from sphinxtrain folder error is showing:

You must run this command in an4 folder, not in sphinxtrain folder

--- (Edited on 5/26/2010 14:23 [GMT+0400] by nsh) ---

Re: sphinxtrain runall.pl error

User: amitkr
Date: 5/26/2010 6:31 am

Views: 52
Rating: 1

thanx for ur help..

utils.pm is there in SphinxTrain/scripts_pl/lib/SphinxTrain

and line 45 has use SphinxTrain::Util; in slave.pl in SphinxTrain/scripts_pl/decode folder

I'hv copied the slave.pl file from sphinxtrain and saved it in the an4's decode folder,after this i gave the following command:

[root@Bharati-Speech an4]# perl scripts_pl/decode/slave.pl

MODULE: DECODE Decoding using models previously trained
Aligning results to find error rate
Can't open for reading

I tried outside root also:

[bharati@Bharati-Speech an4]$ perl scripts_pl/decode/slave.pl

MODULE: DECODE Decoding using models previously trained
Aligning results to find error rate
Can't open file /.match

It's giving this...where will i get /.match file ..I've read an4.html file i didn't get any thing..what nxt i shld do ...plzzz hlp as I'm alone and new to dis field..

--- (Edited on 5/26/2010 6:31 am [GMT-0500] by amitkr) ---

--- (Edited on 5/26/2010 8:40 am [GMT-0500] by amitkr) ---

Re: sphinxtrain runall.pl error

User: nsh
Date: 5/26/2010 12:09 pm

Views: 50
Rating: 1

> what nxt i shld do

Check the log in an4/logdir/decode

--- (Edited on 5/26/2010 21:09 [GMT+0400] by nsh) ---

Re: sphinxtrain runall.pl error

User: Visitor
Date: 5/27/2010 1:30 am

Views: 232
Rating: 1

hi,

thanks for the reply

I didn't get any decode folder in an4/lodir.there r the following folders:

01.vector_quantize

20.ci_hmm

30.cd_hmm_untied

40.buildtrees

45.prunetree

50.cd_hmm_tied

90.deleted_interpolation

99.make_s2_models

I'm sending u my logfile:

MODULE: 00 verify training files (2010-05-27 17:13)

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

passed

Phase 2: DICT - Checking to make sure there are not duplicate entries in the dictionary

passed

Phase 3: CTL - Check general format; utterance length (must be positive); files exist

passed

Phase 4: CTL - Checking number of lines in the transcript should match lines in control file

passed

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

WARNING

Phase 6: TRANSCRIPT - Checking that all the words in the transcript are in the dictionary

Words in dictionary: 130

Words in filler dictionary: 3

passed

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

passed

MODULE: 01 Vector Quantization (2010-05-27 17:13)

agg_seg Log File

completed

kmeans_init Log File

completed

MODULE: 02 Training Context Independent models for forced alignment and VTLN (2010-05-27 17:15)

Skipped: $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg

Skipped: $ST::CFG_VTLN set to 'no' in sphinx_train.cfg

MODULE: 03 Force-aligning transcripts (2010-05-27 17:16)

Skipped: $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg

MODULE: 04 Force-aligning data for VTLN (2010-05-27 17:16)

Skipped: $ST::CFG_VTLN set to 'no' in sphinx_train.cfg

MODULE: 05 Train LDA transformation (2010-05-27 17:16)

Skipped (set $CFG_LDA_MLLT = 'yes' to enable)

MODULE: 06 Train MLLT transformation (2010-05-27 17:17)

Skipped (set $CFG_LDA_MLLT = 'yes' to enable)

MODULE: 20 Training Context Independent models (2010-05-27 17:17)

Phase 1: Cleaning up directories:

accumulator... logs... qmanager... models... completed

Phase 2: Flat initialize

mk_mdef_gen Log File

completed

mk_flat Log File

completed

Phase 3: Forward-Backward

Baum welch starting for 1 Gaussian(s), iteration: 1 (1 of 1)

bw Log File

completed

Normalization for iteration: 1

norm Log File

This step had 10 ERROR messages and 37 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = -11.1623370992029

Baum welch starting for 1 Gaussian(s), iteration: 2 (1 of 1)

bw Log File

completed

Normalization for iteration: 2

norm Log File

WARNING: This step had 0 ERROR messages and 33 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = -0.59943117761607

Convergence Ratio = 0.946298774863297

Baum welch starting for 1 Gaussian(s), iteration: 3 (1 of 1)

bw Log File

completed

Normalization for iteration: 3

norm Log File

WARNING: This step had 0 ERROR messages and 33 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 2.29680190159333

Convergence Ratio = 4.83163570291369

Baum welch starting for 1 Gaussian(s), iteration: 4 (1 of 1)

bw Log File

completed

Normalization for iteration: 4

norm Log File

WARNING: This step had 0 ERROR messages and 29 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 3.61902736496874

Convergence Ratio = 0.575681107917126

Baum welch starting for 1 Gaussian(s), iteration: 5 (1 of 1)

bw Log File

completed

Normalization for iteration: 5

norm Log File

WARNING: This step had 0 ERROR messages and 29 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 4.21079540527117

Convergence Ratio = 0.163515768361021

Baum welch starting for 1 Gaussian(s), iteration: 6 (1 of 1)

bw Log File

completed

Normalization for iteration: 6

norm Log File

WARNING: This step had 0 ERROR messages and 29 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 4.50940153420424

Convergence Ratio = 0.0709144235693021

Baum welch starting for 1 Gaussian(s), iteration: 7 (1 of 1)

bw Log File

completed

Normalization for iteration: 7

norm Log File

WARNING: This step had 0 ERROR messages and 29 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 4.68885060824181

Training completed after 7 iterations

MODULE: 30 Training Context Dependent models (2010-05-27 17:23)

Phase 1: Cleaning up directories:

accumulator... logs... qmanager... completed

Phase 2: Initialization

mk_mdef_gen Log File

WARNING: This step had 0 ERROR messages and 1 WARNING messages. Please check the log file for details.

completed

init_mixw Log File

completed

Phase 3: Forward-Backward

Baum welch starting for iteration: 1 (1 of 1)

bw Log File

WARNING: This step had 0 ERROR messages and 1 WARNING messages. Please check the log file for details.

completed

Normalization for iteration: 1

norm Log File

WARNING: This step had 0 ERROR messages and 31 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 1.58183867992211

Baum welch starting for iteration: 2 (1 of 1)

bw Log File

WARNING: This step had 0 ERROR messages and 1 WARNING messages. Please check the log file for details.

completed

Normalization for iteration: 2

norm Log File

WARNING: This step had 0 ERROR messages and 31 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 4.48009712947706

Convergence Ratio = 1.83220861036074

Baum welch starting for iteration: 3 (1 of 1)

bw Log File

WARNING: This step had 0 ERROR messages and 1 WARNING messages. Please check the log file for details.

completed

Normalization for iteration: 3

norm Log File

WARNING: This step had 0 ERROR messages and 31 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 4.92541843725609

Convergence Ratio = 0.0993999225706547

Baum welch starting for iteration: 4 (1 of 1)

bw Log File

WARNING: This step had 0 ERROR messages and 1 WARNING messages. Please check the log file for details.

completed

Normalization for iteration: 4

norm Log File

WARNING: This step had 0 ERROR messages and 31 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 5.16773756119867

Convergence Ratio = 0.0491976726504419

Baum welch starting for iteration: 5 (1 of 1)

bw Log File

WARNING: This step had 0 ERROR messages and 1 WARNING messages. Please check the log file for details.

completed

Normalization for iteration: 5

norm Log File

WARNING: This step had 0 ERROR messages and 31 WARNING messages. Please check the log file for details.

completed

Current Overall Likelihood Per Frame = 5.35013520864705

Training completed after 5 iterations

MODULE: 40 Build Trees (2010-05-27 17:26)

Phase 1: Cleaning up old log files...

Phase 2: Make Questions

make_quests Log File

completed

Phase 3: Tree building

Processing each phone with each state

AA 0


Username	Password

Speech Recognition Engines

MODULE: 00 verify training files (2010-05-27 17:13)

MODULE: 01 Vector Quantization (2010-05-27 17:13)

MODULE: 02 Training Context Independent models for forced alignment and VTLN (2010-05-27 17:15)

MODULE: 03 Force-aligning transcripts (2010-05-27 17:16)

MODULE: 04 Force-aligning data for VTLN (2010-05-27 17:16)

MODULE: 05 Train LDA transformation (2010-05-27 17:16)

MODULE: 06 Train MLLT transformation (2010-05-27 17:17)

MODULE: 20 Training Context Independent models (2010-05-27 17:17)

MODULE: 30 Training Context Dependent models (2010-05-27 17:23)

MODULE: 40 Build Trees (2010-05-27 17:26)

MODULE: 45 Prune Trees (2010-05-27 17:50)

MODULE: 50 Training Context dependent models (2010-05-27 17:50)

MODULE: 90 deleted interpolation (2010-05-27 17:58)

MODULE: 99 Convert to Sphinx2 format models (2010-05-27 17:58)

MODULE: DECODE Decoding using models previously trained (2010-05-27 17:59)

MODULE: DECODE Decoding using models previously trained (2010-05-27 17:59)

MODULE: DECODE Decoding using models previously trained (2010-05-27 18:03)

MODULE: DECODE Decoding using models previously trained (2010-05-27 18:03)

MODULE: DECODE Decoding using models previously trained (2010-05-27 18:38)

MODULE: DECODE Decoding using models previously trained (2010-05-27 18:48)

MODULE: DECODE Decoding using models previously trained (2010-05-27 18:56)

MODULE: DECODE Decoding using models previously trained (2010-05-27 18:57)

MODULE: DECODE Decoding using models previously trained (2010-05-28 11:30)