Having problem 10.falign_ci_hmm/slave_convg.

[hidayu kamarudin]

Hi
Nickolay V. Shmyrev,

Sorry, i would like to ask regarding my Sphinx Train result. I've got problem
with the:

scripts_pl/10.falign_ci_hmm/slave_convg.pl

Here are the errors:

$ perl scripts_pl/RunAll.pl
MODULE: 00 verify training files
Phase 1: Checking to see if the dict and filler dict agrees with the phonelist
file.
Found 133 words using 34 phones
Phase 2: Checking to make sure there are not duplicate entries in the
dictionary
Phase 3: Check general format for the fileids file; utterance length (must be
positive); files exist
Phase 4: Checking number of lines in the transcript file should match lines in
fileids file
Phase 5: Determine amount of training data, see if n_tied_states seems
reasonable.
Estimated Total Hours Training: 1.41197777777778
This is a small amount of data, no comment at this time
Phase 6: Checking that all the words in the transcript are in the dictionary
Words in dictionary: 130
Words in filler dictionary: 3
Phase 7: 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
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)

Only 0 parts of 1 of Baum Welch were successfully completed
Parts 1 failed to run!
Training failed in iteration 1
Something failed: (C:/tutor/an4/scripts_pl/10.falign_ci_hmm/slave_convg.pl)

-i have tried to update the codes from the link here,
http://cmusphinx.svn.sourceforge.net/viewvc/cmusphinx/trunk/SphinxTrain/scrip
ts/

but when recompile, still giving the same error:
-hope you can suggest me how to solve on this

thanks a lot

[Nickolay V. Shmyrev]

-hope you can suggest me how to solve on this

Please read the troubleshooting section in the acoustic model training
tutorial:

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

In particular read the last part:

If you want to ask for help about training, try to provide the training
folder or at least logdir. We would be glad to help you.

[hidayu kamarudin]

nshmyrev,

i have pm you on the training folder. Thanks a lot.

[Nickolay V. Shmyrev]

The link you sent is not valid

[hidayu kamarudin]

Hi

nshmyrev

Sorry, here is the link of the file:

https://docs.google.com/open?id=0B9jAxP7ALfLcRVN5dTJKYm9WVGM

Again, thank your for your kindness to check and help on this.

[Nickolay V. Shmyrev]

i have pm you on the training folder. Thanks a lot.

Your training files have wrong format at least. The format must be 16 bit
16khz little-endian. Your data is 8 bit

You also do not have enough data to train the model

For more information on training read the tutorial carefully

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