Limit on Number of phones

[Sreenadh TC]

Hi,
I am currently working on developing LM and AM for Malayalam Language using a dictionary of 7048 words. I came across this error, while training the acoustic model.

MODULE: DECODE Decoding using models previously trained
        Aligning results to find error rate
Can't open /home/madboy/Projects/GSoC/ml/result/ml-1-1.match
word_align.pl failed with error code 65280 at /usr/local/lib/sphinxtrain/scripts/decode/slave.pl line 173.
Sphinxtrain path: /usr/local/lib/sphinxtrain
Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
Running the training

So, I checked the logdir, and the same is below,

        INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from /home/madboy/Projects/GSoC/ml/model_parameters/ml.ci_cont/feat.params
Current configuration:
[NAME]          [DEFLT]     [VALUE]
-agc            none        none
-agcthresh      2.0     2.000000e+00
-allphone               
-allphone_ci        no      no
-alpha          0.97        9.700000e-01
-ascale         20.0        2.000000e+01
-aw         1       1
-backtrace      no      no
-beam           1e-48       1.000000e-80
-bestpath       yes     yes
-bestpathlw     9.5     1.000000e+01
-ceplen         13      13
-cmn            current     current
-cmninit        8.0     8.0
-compallsen     no      no
-debug                  0
-dict                   /home/madboy/Projects/GSoC/ml/etc/ml.dic
-dictcase       no      no
-dither         no      no
-doublebw       no      no
-ds         1       1
-fdict                  
-feat           1s_c_d_dd   1s_c_d_dd
-featparams             
-fillprob       1e-8        1.000000e-08
-frate          100     100
-fsg                    
-fsgusealtpron      yes     yes
-fsgusefiller       yes     yes
-fwdflat        yes     yes
-fwdflatbeam        1e-64       1.000000e-80
-fwdflatefwid       4       4
-fwdflatlw      8.5     1.000000e+01
-fwdflatsfwin       25      25
-fwdflatwbeam       7e-29       1.000000e-40
-fwdtree        yes     yes
-hmm                    /home/madboy/Projects/GSoC/ml/model_parameters/ml.ci_cont
-input_endian       little      little
-jsgf                   
-keyphrase              
-kws                    
-kws_delay      10      10
-kws_plp        1e-1        1.000000e-01
-kws_threshold      1       1.000000e+00
-latsize        5000        5000
-lda                    
-ldadim         0       0
-lifter         0       22
-lm                 /home/madboy/Projects/GSoC/ml/etc/ml.bin
-lmctl                  
-lmname                 
-logbase        1.0001      1.000100e+00
-logfn                  
-logspec        no      no
-lowerf         133.33334   1.300000e+02
-lpbeam         1e-40       1.000000e-80
-lponlybeam     7e-29       1.000000e-80
-lw         6.5     1.000000e+01
-maxhmmpf       30000       30000
-maxwpf         -1      -1
-mdef                   
-mean                   
-mfclogdir              
-min_endfr      0       0
-mixw                   
-mixwfloor      0.0000001   1.000000e-07
-mllr                   
-mmap           yes     yes
-ncep           13      13
-nfft           512     512
-nfilt          40      25
-nwpen          1.0     1.000000e+00
-pbeam          1e-48       1.000000e-80
-pip            1.0     1.000000e+00
-pl_beam        1e-10       1.000000e-10
-pl_pbeam       1e-10       1.000000e-10
-pl_pip         1.0     1.000000e+00
-pl_weight      3.0     3.000000e+00
-pl_window      5       5
-rawlogdir              
-remove_dc      no      no
-remove_noise       yes     yes
-remove_silence     yes     yes
-round_filters      yes     yes
-samprate       16000       1.600000e+04
-seed           -1      -1
-sendump                
-senlogdir              
-senmgau                
-silprob        0.005       5.000000e-03
-smoothspec     no      no
-svspec                 
-tmat                   
-tmatfloor      0.0001      1.000000e-04
-topn           4       4
-topn_beam      0       0
-toprule                
-transform      legacy      dct
-unit_area      yes     yes
-upperf         6855.4976   6.800000e+03
-uw         1.0     1.000000e+00
-vad_postspeech     50      50
-vad_prespeech      20      20
-vad_startspeech    10      10
-vad_threshold      2.0     2.000000e+00
-var                    
-varfloor       0.0001      1.000000e-04
-varnorm        no      no
-verbose        no      no
-warp_params                
-warp_type      inverse_linear  inverse_linear
-wbeam          7e-29       1.000000e-40
-wip            0.65        2.000000e-01
-wlen           0.025625    2.562500e-02

INFO: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(143): mean[0]= 12.00, mean[1..12]= 0.0
INFO: mdef.c(518): Reading model definition: /home/madboy/Projects/GSoC/ml/model_parameters/ml.ci_cont/mdef
ERROR: "bin_mdef.c", line 92: Number of phones exceeds limit: 842 > 255
INFO: bin_mdef.c(336): Reading binary model definition: /home/madboy/Projects/GSoC/ml/model_parameters/ml.ci_cont/mdef
ERROR: "bin_mdef.c", line 360: File format version 1634887022 for /home/madboy/Projects/GSoC/ml/model_parameters/ml.ci_cont/mdef is newer than library
ERROR: "acmod.c", line 89: Failed to read acoustic model definition from /home/madboy/Projects/GSoC/ml/model_parameters/ml.ci_cont/mdef
FATAL: "batch.c", line 822: PocketSphinx decoder init failed
Sun Jul 17 20:16:35 2016

I also saw one discussion regarding the phone limit here.
Can anyone say what I can do to make this work. It too hard to change that many phones for a dicionary of such scale.

Do let me know if there is a need for more files.

[Nickolay V. Shmyrev]

Your phoneset size should be less than 255. You need to use phone-based phoneset, not syllable-based phoneset.

[Sreenadh TC]

OH!
Okay, I get it now. Thanks man.
It would be good if someone could add this in the Wiki Tutorial section where each file is explained. At least about the limit. Ignore if it is metioned elsewhere. I didn't see much info on this.