Menu

Error running RunAll.pl script

Help
2011-02-17
2012-09-22
  • Rajat Agrawal

    Rajat Agrawal - 2011-02-17

    Hi !

    While running the ./scripts_pl/RunAll.pl script after making features for my
    database, I am getting the following error on running this script ,

    " Only 0 parts of 1 of Baum Welch were successfully completed
    Parts 1 failed to run!
    Training failed in iteration 1
    Something failed:
    (<databasedirectory>/scripts_pl/30.cd_hmm_untied/slave_convg.pl)" </databasedirectory>

    In the log file, I am getting the following error message :

    " ... timing info ...
    utt> 0 FM014001 199 0WARNING: "corpus.c", line 1986: LSN utt id,
    train/FM014001, does not match ctl utt id, FM014001. "

    where FM014001 is a name of one of the files for acoustic model training..

    I would be glad to receive any assistance to solve the issue..

     
  • Rajat Agrawal

    Rajat Agrawal - 2011-02-17

    A little more verbose message on running the ./scripts_pl/RunAll.pl scripts is
    "

    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% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    WARNING: This step had 0 ERROR messages and 4949 WARNING messages. Please
    check the log file for details.
    Normalization for iteration: 1
    Current Overall Likelihood Per Frame = 1.52210816251144
    Baum welch starting for 1 Gaussian(s), iteration: 2 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 6 ERROR messages and 4949 WARNING messages. Please check the log
    file for details.
    Normalization for iteration: 2
    Current Overall Likelihood Per Frame = 5.16627780203531
    Convergence Ratio = 2.39415944889953
    Baum welch starting for 1 Gaussian(s), iteration: 3 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 24 ERROR messages and 4958 WARNING messages. Please check the
    log file for details.
    Normalization for iteration: 3
    Current Overall Likelihood Per Frame = 7.27011691792115
    Convergence Ratio = 0.407225317046832
    Baum welch starting for 1 Gaussian(s), iteration: 4 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 28 ERROR messages and 4960 WARNING messages. Please check the
    log file for details.
    Normalization for iteration: 4
    Current Overall Likelihood Per Frame = 7.74718202947617
    Convergence Ratio = 0.0656200054195879
    Baum welch starting for 1 Gaussian(s), iteration: 5 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 28 ERROR messages and 4960 WARNING messages. Please check the
    log file for details.
    Normalization for iteration: 5
    Current Overall Likelihood Per Frame = 7.88228608278586
    Training completed after 5 iterations
    MODULE: 30 Training Context Dependent models
    Phase 1: Cleaning up directories:
    accumulator...logs...qmanager...
    Phase 2: Initialization
    WARNING: This step had 0 ERROR messages and 1 WARNING messages. Please check
    the log file for details.
    Phase 3: Forward-Backward
    Baum welch starting for iteration: 1 (1 of 1)
    0%
    WARNING: This step had 0 ERROR messages and 3 WARNING messages. Please check
    the log file for details.
    Only 0 parts of 1 of Baum Welch were successfully completed
    Parts 1 failed to run!
    Training failed in iteration 1
    Something failed: (<database directory="">/scripts_pl/30.cd_hmm_untied/slave_convg.pl) </database>

    "

    Thanks,

     
  • Nickolay V. Shmyrev

    Such error is usually caused by spaces in phoneset file or by phones which can
    be only distinguised by case like "e" and "E" in your phoneset.

    Usually you just need to read log carefully to understand what is the problem
    because everything is described in the log in plain English words. Reading the
    log doesn't mean picking the single one but it means that you need to check
    every log in the logdir starting from the most recent one and going back.

    Tutorial covers everything in details, including troubleshoot practices.
    Please check it

    http://cmusphinx.sourceforge.net/wiki/tutorialam

     
  • Rajat Agrawal

    Rajat Agrawal - 2011-02-18

    Thank you very much for the assistance.

     

Log in to post a comment.