Training an acoustic model for CMUSphinx Failing

[Ali]

When training an acoustic model , I successfully prepared data , compile the requied packages , run the train script and since I am using all default configuration so there is no change on etc/sphinx_train.cfg file .

You can download file structure with the link below to see if I made any mistake ,
File Structure

Below is the picture of my root folder
tutorial folder root directory inside

When run the folowing command
sphinxtrain run

I got these error logs

Alis-MacBook-Pro:an4 aliakhtar$ sphinxtrain run
Sphinxtrain path: /usr/local/lib/sphinxtrain
Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
Running the training
MODULE: 000 Computing feature from audio files
Failed to open control file /Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.fileids: No such file or directory at /usr/local/lib/sphinxtrain/scripts/000.comp_feat/make_feats.pl line 89.
Failed to open control file /Users/aliakhtar/Documents/tutorial/an4/etc/an4_test.fileids: No such file or directory at /usr/local/lib/sphinxtrain/scripts/000.comp_feat/make_feats.pl line 89.
Feature extraction is done
MODULE: 00 verify training files
Can not open the dictionary (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.dic) at /usr/local/lib/sphinxtrain/scripts/00.verify/verify_all.pl line 58.

I am using macOS Sierra 10.12.6 , Can someone help me what I am doing wrong , I made my own an4 folder with language model in ARPA format ,

[Nickolay V. Shmyrev]

Files in etc folder should have name an4_test, not a4_test like in your case. You miss letter 'n' in filename.

[Ali]

Got these logs after fixing name of the file ,

Alis-MacBook-Pro:an4 aliakhtar$ sphinxtrain run
Sphinxtrain path: /usr/local/lib/sphinxtrain
Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
Running the training
MODULE: 000 Computing feature from audio files
Extracting features from  segments starting at  (part 1 of 1) 
Extracting features from  segments starting at  (part 1 of 1) 
ERROR: This step had 1 ERROR messages and 0 WARNING messages.  Please check the log file for details.
Feature extraction is done
MODULE: 00 verify training files
    Phase 1: Checking to see if the dict and filler dict agrees with the phonelist file.
        Found 27 words using 30 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: 0.005675
ERROR: Not enough data for the training, we can only train CI models (set CFG_CD_TRAIN to "no")
    Phase 6: Checking that all the words in the transcript are in the dictionary
        Words in dictionary: 24
        Words in filler dictionary: 3
WARNING: This word: ONE</s> was in the transcript file, but is not in the dictionary (<s> ONE ONE</s> ). Do cases match?
    Phase 7: Checking that all the phones in the transcript are in the phonelist, and all phones in the phonelist appear at least once
WARNING: This phone (AE) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (AW) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (B) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (D) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (ER) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (HH) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (L) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (M) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (OW) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (P) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (Y) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)
WARNING: This phone (Z) occurs in the phonelist (/Users/aliakhtar/Documents/tutorial/an4/etc/an4.phone), but not in any word in the transcription (/Users/aliakhtar/Documents/tutorial/an4/etc/an4_train.transcription)

(ERROR: Not enough data for the training) Should I need to remove this error for successfull training or there are other things which I am missing . ??

If I am making a speech recogntion system that only recognize counting from 1 to 9 ? How much training data I need ?

If i sphinxtrain -t an4 setup , then (set CFG_CD_TRAIN to "no") , then run sphinxtrain run , I got these errors

Alis-MacBook-Pro:an4 aliakhtar$ sphinxtrain run
Sphinxtrain path: /usr/local/lib/sphinxtrain
Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
Running the training
Configuration (e.g. etc/sphinx_train.cfg) not defined
Compilation failed in require at /usr/local/lib/sphinxtrain/scripts/000.comp_feat/slave_feat.pl line 51.
BEGIN failed--compilation aborted at /usr/local/lib/sphinxtrain/scripts/000.comp_feat/slave_feat.pl line 51.
Alis-MacBook-Pro:an4 aliakhtar$ 

[Nickolay V. Shmyrev]

Data requirements are listed in tutorial

http://cmusphinx.github.io/wiki/tutorialam

1 hour of recording for command and control for a single speaker
5 hours of recordings of 200 speakers for command and control for many speakers
10 hours of recordings for single speaker dictation
50 hours of recordings of 200 speakers for many speakers dictation

[Ali]

Is my training successfully done ??

Alis-MacBook-Pro:an4 aliakhtar$ sphinxtrain run
Sphinxtrain path: /usr/local/lib/sphinxtrain
Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
Running the training
MODULE: 000 Computing feature from audio files
Extracting features from  segments starting at  (part 1 of 1) 
Extracting features from  segments starting at  (part 1 of 1) 
Feature extraction is done
MODULE: 00 verify training files
    Phase 1: Checking to see if the dict and filler dict agrees with the phonelist file.
        Found 12 words using 18 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: 0.584030555555555
        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: 9
        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: 0000 train grapheme-to-phoneme model
Skipped (set $CFG_G2P_MODEL = 'yes' to enable)
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 'no' 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 'no' in sphinx_train.cfg
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% 30% 50% 80% 100% 
        Normalization for iteration: 1
        Current Overall Likelihood Per Frame = -152.747953636368
        Baum welch starting for 1 Gaussian(s), iteration: 2 (1 of 1)
        0% 30% 50% 80% 100% 
        Normalization for iteration: 2
        Current Overall Likelihood Per Frame = -152.098301553857
        Convergence Ratio = 0.649652082510954
        Baum welch starting for 1 Gaussian(s), iteration: 3 (1 of 1)
        0% 30% 50% 80% 100% 
        Normalization for iteration: 3
WARNING: *WARNING*: NEGATIVE CONVERGENCE RATIO AT ITER 3! CHECK BW AND NORM LOGFILES
        Current Overall Likelihood Per Frame = -152.683649542689
        Training completed after 3 iterations
MODULE: 30 Training Context Dependent models
    Phase 1: Cleaning up directories:
    accumulator...logs...qmanager...
    Phase 2: Initialization
    Phase 3: Forward-Backward
        Baum welch starting for iteration: 1 (1 of 1) 
        0% 30% 50% 80% 100% 
        Normalization for iteration: 1
        Current Overall Likelihood Per Frame = -147.770807273212
        Baum welch starting for iteration: 2 (1 of 1) 
        0% 30% 50% 80% 100% 
        Normalization for iteration: 2
        Current Overall Likelihood Per Frame = -146.855567868881
        Convergence Ratio = 0.915239404331459
        Baum welch starting for iteration: 3 (1 of 1) 
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 3
        Current Overall Likelihood Per Frame = -146.657699138641
        Convergence Ratio = 0.197868730239833
        Baum welch starting for iteration: 4 (1 of 1) 
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 4
        Current Overall Likelihood Per Frame = -146.59675169153
        Training completed after 4 iterations
MODULE: 40 Build Trees
    Phase 1: Cleaning up old log files...
    Phase 2: Make Questions
    Phase 3: Tree building
        Processing each phone with each state
        EY 0 
        EY 1 
        EY 2 
        T 0 
        T 1 
        T 2 
        F 0 
        F 1 
        F 2 
        AY 0 
        AY 1 
        AY 2 
        V 0 
        V 1 
        V 2 
        AO 0 
        AO 1 
        AO 2 
        R 0 
        R 1 
        R 2 
        W 0 
        W 1 
        W 2 
        AH 0 
        AH 1 
        AH 2 
        N 0 
        N 1 
        N 2 
        S 0 
        S 1 
        S 2 
        EH 0 
        EH 1 
        EH 2 
        IH 0 
        IH 1 
        IH 2 
        K 0 
        K 1 
        K 2 
        TH 0 
        TH 1 
        TH 2 
        IY 0 
        IY 1 
        IY 2 
        UW 0 
        UW 1 
        UW 2 
        Skipping SIL
MODULE: 45 Prune Trees
    Phase 1: Tree Pruning
    Phase 2: State Tying
MODULE: 50 Training Context dependent models
    Phase 1: Cleaning up directories:
    accumulator...logs...qmanager...
    Phase 2: Copy CI to CD initialize
    Phase 3: Forward-Backward
        Baum welch starting for 1 Gaussian(s), iteration: 1 (1 of 1)
        0% 30% 50% 80% 100% 
        Normalization for iteration: 1
        Current Overall Likelihood Per Frame = -147.770807273212
        Baum welch starting for 1 Gaussian(s), iteration: 2 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 2
        Current Overall Likelihood Per Frame = -146.767928310565
        Convergence Ratio = 1.00287896264666
        Baum welch starting for 1 Gaussian(s), iteration: 3 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 3
        Current Overall Likelihood Per Frame = -146.658556212116
        Convergence Ratio = 0.10937209844883
        Baum welch starting for 1 Gaussian(s), iteration: 4 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 4
        Current Overall Likelihood Per Frame = -146.594799468614
        Split Gaussians, increase by 1
        Current Overall Likelihood Per Frame = -146.594799468614
        Convergence Ratio = 0.0637567435015569
        Baum welch starting for 2 Gaussian(s), iteration: 1 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 1
        Current Overall Likelihood Per Frame = -146.902346000562
        Baum welch starting for 2 Gaussian(s), iteration: 2 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 2
        Current Overall Likelihood Per Frame = -146.008608826904
        Convergence Ratio = 0.893737173657513
        Baum welch starting for 2 Gaussian(s), iteration: 3 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 3
        Current Overall Likelihood Per Frame = -144.674431117481
        Convergence Ratio = 1.33417770942305
        Baum welch starting for 2 Gaussian(s), iteration: 4 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 4
        Current Overall Likelihood Per Frame = -143.797740182938
        Convergence Ratio = 0.876690934543433
        Baum welch starting for 2 Gaussian(s), iteration: 5 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 5
        Current Overall Likelihood Per Frame = -143.513239404429
        Convergence Ratio = 0.284500778508857
        Baum welch starting for 2 Gaussian(s), iteration: 6 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 6
        Current Overall Likelihood Per Frame = -143.352538127866
        Convergence Ratio = 0.160701276563145
        Baum welch starting for 2 Gaussian(s), iteration: 7 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 7
        Current Overall Likelihood Per Frame = -143.285972087974
        Split Gaussians, increase by 2
        Current Overall Likelihood Per Frame = -143.285972087974
        Convergence Ratio = 0.0665660398921943
        Baum welch starting for 4 Gaussian(s), iteration: 1 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 1
ERROR: This step had 39 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Current Overall Likelihood Per Frame = -143.560711751906
        Baum welch starting for 4 Gaussian(s), iteration: 2 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 2
        Current Overall Likelihood Per Frame = -142.477323264307
        Convergence Ratio = 1.08338848759882
        Baum welch starting for 4 Gaussian(s), iteration: 3 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 3
        Current Overall Likelihood Per Frame = -141.540161034583
        Convergence Ratio = 0.937162229724066
        Baum welch starting for 4 Gaussian(s), iteration: 4 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 4
        Current Overall Likelihood Per Frame = -140.783555616926
        Convergence Ratio = 0.756605417656772
        Baum welch starting for 4 Gaussian(s), iteration: 5 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 5
        Current Overall Likelihood Per Frame = -140.452249103644
        Convergence Ratio = 0.331306513282016
        Baum welch starting for 4 Gaussian(s), iteration: 6 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 6
        Current Overall Likelihood Per Frame = -140.26816876729
        Convergence Ratio = 0.18408033635373
        Baum welch starting for 4 Gaussian(s), iteration: 7 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 7
        Current Overall Likelihood Per Frame = -140.164605722394
        Convergence Ratio = 0.103563044896106
        Baum welch starting for 4 Gaussian(s), iteration: 8 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 8
        Current Overall Likelihood Per Frame = -140.100134750996
        Split Gaussians, increase by 4
        Current Overall Likelihood Per Frame = -140.100134750996
        Convergence Ratio = 0.0644709713976397
        Baum welch starting for 8 Gaussian(s), iteration: 1 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 1
ERROR: This step had 440 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Current Overall Likelihood Per Frame = -140.392015884428
        Baum welch starting for 8 Gaussian(s), iteration: 2 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 2
        Current Overall Likelihood Per Frame = -138.803906350438
        Convergence Ratio = 1.58810953398969
        Baum welch starting for 8 Gaussian(s), iteration: 3 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 3
        Current Overall Likelihood Per Frame = -137.292552507654
        Convergence Ratio = 1.51135384278388
        Baum welch starting for 8 Gaussian(s), iteration: 4 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 4
        Current Overall Likelihood Per Frame = -135.505982849007
        Convergence Ratio = 1.78656965864653
        Baum welch starting for 8 Gaussian(s), iteration: 5 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 5
        Current Overall Likelihood Per Frame = -135.109062599694
        Convergence Ratio = 0.3969202493127
        Baum welch starting for 8 Gaussian(s), iteration: 6 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 6
        Current Overall Likelihood Per Frame = -134.979263583424
        Convergence Ratio = 0.1297990162698
        Baum welch starting for 8 Gaussian(s), iteration: 7 (1 of 1)
        0% 30% 50% 80% 100% 
ERROR: This step had 2 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Normalization for iteration: 7
        Current Overall Likelihood Per Frame = -134.904841036678
Training for 8 Gaussian(s) completed after 7 iterations
MODULE: 60 Lattice Generation
Skipped:  $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 61 Lattice Pruning
Skipped:  $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 62 Lattice Format Conversion
Skipped:  $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 65 MMIE Training
Skipped:  $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 90 deleted interpolation
Skipped for continuous models
MODULE: DECODE Decoding using models previously trained
        Decoding 37 segments starting at 0 (part 1 of 1) 
        0% 
        Aligning results to find error rate
Can't open /Users/aliakhtar/Documents/tutorial/an4/result/an4-1-1.match
word_align.pl failed with error code 65280 at /usr/local/lib/sphinxtrain/scripts/decode/slave.pl line 173.

[Ali]

Can anyone relpy on above post ?
Or can someone provide whole database folder that was successfully trained and tested so I can compile at my side and made by folder same like that ?

Another thing should I need to replace

$DEC_CFG_LANGUAGEMODEL  = "$CFG_BASE_DIR/etc/${CFG_DB_NAME}.lm.DMP";

with

$DEC_CFG_LANGUAGEMODEL  = "$CFG_BASE_DIR/etc/${CFG_DB_NAME}.lm";

on my sphinx_train.cfg Since I have a langugae model file with extension lm only on my database folder

Thanks

[Nickolay V. Shmyrev]

Can anyone relpy on above post ?

No, your model was not trained successfully. It is pretty clear that there was error in decoding.

Or can someone provide whole database folder that was successfully trained and tested so I can compile at my side and made by folder same like that ?

An4 link is provided in tutorial.

Another thing should I need to replace
$DEC_CFG_LANGUAGEMODEL = "$CFG_BASE_DIR/etc/${CFG_DB_NAME}.lm.DMP";
with
$DEC_CFG_LANGUAGEMODEL = "$CFG_BASE_DIR/etc/${CFG_DB_NAME}.lm";
on my sphinx_train.cfg Since I have a langugae model file with extension lm only on my database folder

Yes

[Ali]

I was not compiling pocketsphinx
I am succusscfully train an acoustic model using an4 database that is provided

Now I need to train it on my own database

Special thank Nickolay V. Shmyrev , for replying my post

[Giro Rarielli]

Hi,
Did you use Your format of files in databases or format from the database that is given in tutorial?