Menu

acoustic model with LDA and MLLT feature tran

Help
Anonymous
2012-05-03
2016-01-20
  • Anonymous

    Anonymous - 2012-05-03

    iam trying to Train an acoustic model with LDA and MLLT feature transforms and
    this error lda.py failed to create LDA transform with status 0
    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 9719 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.
    Estimated Total Hours Training: 19.1418194444444
    Rule of thumb suggests 3000, however there is no correct answer
    Phase 6: TRANSCRIPT - Checking that all the words in the transcript are in the
    dictionary
    Words in dictionary: 9716
    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
    Phase 1: Cleaning up directories:
    accumulator...logs...qmanager...
    Phase 2: Flat initialize
    Phase 3: Forward-Backward
    Baum welch starting for LDA, iteration: 1 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    Normalization for iteration: 1
    Current Overall Likelihood Per Frame = -6.0700154040274
    Baum welch starting for LDA, iteration: 2 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 4 ERROR messages and 0 WARNING messages. Please check the log
    file for details.
    Normalization for iteration: 2
    Current Overall Likelihood Per Frame = -4.13318286357249
    Convergence Ratio = 1.93683254045491
    Baum welch starting for LDA, iteration: 3 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 20 ERROR messages and 3 WARNING messages. Please check the log
    file for details.
    Normalization for iteration: 3
    Current Overall Likelihood Per Frame = -1.87428922287981
    Convergence Ratio = 2.25889364069268
    Baum welch starting for LDA, iteration: 4 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 12 ERROR messages and 3 WARNING messages. Please check the log
    file for details.
    Normalization for iteration: 4
    Current Overall Likelihood Per Frame = -0.793493780044199
    Convergence Ratio = 1.08079544283561
    Baum welch starting for LDA, iteration: 5 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 36 ERROR messages and 12 WARNING messages. Please check the log
    file for details.
    Normalization for iteration: 5
    Current Overall Likelihood Per Frame = -0.523991171419759
    Convergence Ratio = 0.26950260862444
    Baum welch starting for LDA, iteration: 6 (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 44 ERROR messages and 13 WARNING messages. Please check the log
    file for details.
    Normalization for iteration: 6
    Current Overall Likelihood Per Frame = -0.457759958057266
    Current Overall Likelihood Per Frame = -0.457759958057266
    Convergence Ratio = 0.0662312133624935
    Phase 4: LDA transform estimation
    Baum welch starting for LDA, iteration: N (1 of 1)
    0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
    This step had 46 ERROR messages and 13 WARNING messages. Please check the log
    file for details.
    lda.py failed to create LDA transform with status 0
    LDA Training failed
    any idea what is the problem ?

     
  • Nickolay V. Shmyrev

    You do not have scipy and numpy installed. Please consult documentation for
    more details.

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

    Please check logs in logdir folder for more details. Please read
    troubleshooting section in the acoustic model training tutorial in order to be
    able to solve the acoustic model training problems quickly.

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

     
  • Anonymous

    Anonymous - 2012-05-06

    no i have installed scipy and numpy and i test them as the tutoria
    l >>> import numpy

    import scipy
    import scipy.optimize

    but i can't find lda.py file

     
  • Nickolay V. Shmyrev

    The file lda.py is a part of SphinxTrain package

    SphinxTrain/python/cmusphinx/lda.py
    
     
  • Anonymous

    Anonymous - 2012-05-06

    the problem have been solved ,thank you

     
    • virginia

      virginia - 2016-01-20

      Hi, please post how or what solved the problem. You are not alone!. V.

       

Log in to post a comment.