CMU Sphinx / Forums / Help: Using a Pocketsphinx model

Hello,

I have a Croatian "alphanumeric" acoustic model with the decode slave giving a
7% WER.

Now, I would like to use this model for decoding individual new files, but the
results aren't nearly as good. I tried running
this
Pyhton script, only with my own models on some of the files I used in the
training and testing, but the only output is zero or one letters, usually
wrong.

I noticed that there is no way to specify the decoding parameters (such as the
sampling rate etc.). Is it possible to give the script a sphinx_decode.cfg
file? Can it somehow be achieved in pocketsphinx_batch? I didn't find much
info about this in the man page.

If I try running pocketsphinx_continuous I don't see any output in the
terminal and there isn't a hyp file anywhere, either.

This is the output I get after running pocketsphinx_continuous:

kermit@hocus-pocus:~/programi/sphinx/cro-anclear

kermit@hocus-pocus:~/programi/sphinx/cro-an$ pocketsphinx_continuous -hmm model_parameters/cro-an.cd_cont_1000 -lm etc/cro-an.lm.DMP -dict etc/cro-an.dic
INFO: cmd_ln.c(512): Parsing command line:
pocketsphinx_continuous \
    -hmm model_parameters/cro-an.cd_cont_1000 \
    -lm etc/cro-an.lm.DMP \
    -dict etc/cro-an.dic

Current configuration:
[NAME]      [DEFLT]     [VALUE]
-adcdev             
-agc        none        none
-agcthresh  2.0     2.000000e+00
-alpha      0.97        9.700000e-01
-argfile            
-ascale     20.0        2.000000e+01
-backtrace  no      no
-beam       1e-48       1.000000e-48
-bestpath   yes     yes
-bestpathlw 9.5     9.500000e+00
-bghist     no      no
-ceplen     13      13
-cmn        current     current
-cmninit    8.0     8.0
-compallsen no      no
-debug              0
-dict               etc/cro-an.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-64
-fwdflatefwid   4       4
-fwdflatlw  8.5     8.500000e+00
-fwdflatsfwin   25      25
-fwdflatwbeam   7e-29       7.000000e-29
-fwdtree    yes     yes
-hmm                model_parameters/cro-an.cd_cont_1000
-input_endian   little      little
-jsgf               
-kdmaxbbi   -1      -1
-kdmaxdepth 0       0
-kdtree             
-latsize    5000        5000
-lda                
-ldadim     0       0
-lextreedump    0       0
-lifter     0       0
-lm             etc/cro-an.lm.DMP
-lmctl              
-lmname     default     default
-logbase    1.0001      1.000100e+00
-logfn              
-logspec    no      no
-lowerf     133.33334   1.333333e+02
-lpbeam     1e-40       1.000000e-40
-lponlybeam 7e-29       7.000000e-29
-lw     6.5     6.500000e+00
-maxhmmpf   -1      -1
-maxnewoov  20      20
-maxwpf     -1      -1
-mdef               
-mean               
-mfclogdir          
-mixw               
-mixwfloor  0.0000001   1.000000e-07
-mllr               
-mmap       yes     yes
-ncep       13      13
-nfft       512     512
-nfilt      40      40
-nwpen      1.0     1.000000e+00
-pbeam      1e-48       1.000000e-48
-pip        1.0     1.000000e+00
-pl_beam    1e-10       1.000000e-10
-pl_pbeam   1e-5        1.000000e-05
-pl_window  0       0
-rawlogdir          
-remove_dc  no      no
-round_filters  yes     yes
-samprate   16000       1.600000e+04
-seed       -1      -1
-sendump            
-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      legacy
-unit_area  yes     yes
-upperf     6855.4976   6.855498e+03
-usewdphones    no      no
-uw     1.0     1.000000e+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       7.000000e-29
-wip        0.65        6.500000e-01
-wlen       0.025625    2.562500e-02

INFO: cmd_ln.c(512): Parsing command line:
\
    -alpha 0.97 \
    -dither yes \
    -doublebw no \
    -nfilt 40 \
    -ncep 13 \
    -lowerf 133.33334 \
    -upperf 6855.4976 \
    -nfft 512 \
    -wlen 0.0256 \
    -transform legacy \
    -feat 1s_c_d_dd \
    -agc none \
    -cmn current \
    -varnorm no

Current configuration:
[NAME]      [DEFLT]     [VALUE]
-agc        none        none
-agcthresh  2.0     2.000000e+00
-alpha      0.97        9.700000e-01
-ceplen     13      13
-cmn        current     current
-cmninit    8.0     8.0
-dither     no      yes
-doublebw   no      no
-feat       1s_c_d_dd   1s_c_d_dd
-frate      100     100
-input_endian   little      little
-lda                
-ldadim     0       0
-lifter     0       0
-logspec    no      no
-lowerf     133.33334   1.333333e+02
-ncep       13      13
-nfft       512     512
-nfilt      40      40
-remove_dc  no      no
-round_filters  yes     yes
-samprate   16000       1.600000e+04
-seed       -1      -1
-smoothspec no      no
-svspec             
-transform  legacy      legacy
-unit_area  yes     yes
-upperf     6855.4976   6.855498e+03
-varnorm    no      no
-verbose    no      no
-warp_params            
-warp_type  inverse_linear  inverse_linear
-wlen       0.025625    2.560000e-02

INFO: acmod.c(238): Parsed model-specific feature parameters from model_parameters/cro-an.cd_cont_1000/feat.params
INFO: fe_interface.c(288): You are using the internal mechanism to generate the seed.
INFO: feat.c(848): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: mdef.c(520): Reading model definition: model_parameters/cro-an.cd_cont_1000/mdef
INFO: bin_mdef.c(173): Allocating 25282 * 8 bytes (197 KiB) for CD tree
INFO: tmat.c(205): Reading HMM transition probability matrices: model_parameters/cro-an.cd_cont_1000/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: model_parameters/cro-an.cd_cont_1000/means
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: model_parameters/cro-an.cd_cont_1000/variances
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(356): 175292 variance values floored
INFO: acmod.c(119): Attempting to use PTHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: model_parameters/cro-an.cd_cont_1000/means
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: model_parameters/cro-an.cd_cont_1000/variances
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(356): 175292 variance values floored
ERROR: "ptm_mgau.c", line 801: Number of codebooks exceeds 256: 969
INFO: acmod.c(121): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: model_parameters/cro-an.cd_cont_1000/means
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: model_parameters/cro-an.cd_cont_1000/variances
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(356): 175292 variance values floored
INFO: ms_senone.c(160): Reading senone mixture weights: model_parameters/cro-an.cd_cont_1000/mixture_weights
INFO: ms_senone.c(211): Truncating senone logs3(pdf) values by 10 bits
INFO: ms_senone.c(218): Not transposing mixture weights in memory
INFO: ms_senone.c(277): Read mixture weights for 969 senones: 1 features x 8 codewords
INFO: ms_senone.c(331): Mapping senones to individual codebooks
INFO: ms_mgau.c(123): The value of topn: 4
INFO: dict.c(294): Allocating 4137 * 32 bytes (129 KiB) for word entries
INFO: dict.c(306): Reading main dictionary: etc/cro-an.dic
INFO: dict.c(206): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(309): 38 words read
INFO: dict.c(314): Reading filler dictionary: model_parameters/cro-an.cd_cont_1000/noisedict
INFO: dict.c(206): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(317): 3 words read
INFO: dict2pid.c(402): Building PID tables for dictionary
INFO: dict2pid.c(409): Allocating 41 * 8 bytes (0 KiB) for word-internal arrays
INFO: dict2pid.c(414): Allocating 29^3 * 2 bytes (47 KiB) for word-initial triphones
INFO: dict2pid.c(453): Allocating 22 entries of 2 bytes (0 KiB) for internal ssids
INFO: dict2pid.c(130): Allocated 20416 bytes (19 KiB) for word-final triphones
INFO: dict2pid.c(193): Allocated 20416 bytes (19 KiB) for single-phone word triphones
ERROR: "ngram_model_arpa.c", line 76: No \data\ mark in LM file
INFO: ngram_model_dmp.c(141): Will use memory-mapped I/O for LM file
INFO: ngram_model_dmp.c(195): ngrams 1=40, 2=230, 3=378
INFO: ngram_model_dmp.c(241):       40 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(289):      230 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314):      378 = LM.trigrams read
INFO: ngram_model_dmp.c(338):       44 = LM.prob2 entries read
INFO: ngram_model_dmp.c(357):       93 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(377):       29 = LM.prob3 entries read
INFO: ngram_model_dmp.c(405):        1 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(461):       40 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 10 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 32 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 32 single-phone words
INFO: ngram_search_fwdtree.c(324): after: max nonroot chan increased to 150
INFO: ngram_search_fwdtree.c(333): after: 10 root, 22 non-root channels, 31 single-phone words
INFO: ngram_search_fwdflat.c(153): fwdflat: min_ef_width = 4, max_sf_win = 25
Warning: Could not find Mic element
INFO: continuous.c(261): pocketsphinx_continuous COMPILED ON: Apr 10 2010, AT: 22:53:07

READY....
Listening...
Stopped listening, please wait...
INFO: cmn_prior.c(121): cmn_prior_update: from <  8.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00 >
INFO: cmn_prior.c(139): cmn_prior_update: to   < 13.51  0.17 -0.52 -0.30 -0.29 -0.07 -0.25 -0.21 -0.16 -0.12 -0.13 -0.11 -0.14 >
INFO: ngram_search_fwdtree.c(1502):      533 words recognized (1/fr)
INFO: ngram_search_fwdtree.c(1504):    49392 senones evaluated (92/fr)
INFO: ngram_search_fwdtree.c(1506):    17559 channels searched (32/fr), 5320 1st, 12239 last
INFO: ngram_search_fwdtree.c(1510):    12239 words for which last channels evaluated (22/fr)
INFO: ngram_search_fwdtree.c(1513):        0 candidate words for entering last phone (0/fr)
000000000: (null) (-78848)
READY....
Listening...
Stopped listening, please wait...
INFO: cmn_prior.c(121): cmn_prior_update: from < 13.51  0.17 -0.52 -0.30 -0.29 -0.07 -0.25 -0.21 -0.16 -0.12 -0.13 -0.11 -0.14 >
INFO: cmn_prior.c(139): cmn_prior_update: to   < 13.59  0.09 -0.55 -0.29 -0.29 -0.07 -0.23 -0.21 -0.15 -0.12 -0.13 -0.12 -0.15 >
INFO: ngram_search_fwdtree.c(1502):      196 words recognized (2/fr)
INFO: ngram_search_fwdtree.c(1504):     9277 senones evaluated (102/fr)
INFO: ngram_search_fwdtree.c(1506):     3275 channels searched (35/fr), 870 1st, 2405 last
INFO: ngram_search_fwdtree.c(1510):     2405 words for which last channels evaluated (26/fr)
INFO: ngram_search_fwdtree.c(1513):        0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdflat.c(295): Utterance vocabulary contains 1 words
INFO: ngram_search_fwdflat.c(912):      229 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(914):      270 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(916):      313 channels searched (3/fr)
INFO: ngram_search_fwdflat.c(918):      313 words searched (3/fr)
INFO: ngram_search_fwdflat.c(920):       50 word transitions (0/fr)
INFO: ngram_search.c(1137): lattice start node <s>.0 end node </s>.45
INFO: ps_lattice.c(1228): Normalizer P(O) = alpha(</s>:45:89) = -73281
INFO: ps_lattice.c(1266): Joint P(O,S) = -73281 P(S|O) = 0
000000001:  (-1195465)
READY....
Listening...

And this is the output of the aforementioned Python script:

kermit@hocus-pocus:~/programi/sphinx/cro-an$ python cro-an-recogniser.py wav/test/60.wav 
INFO: cmd_ln.c(512): Parsing command line:
\
    -hmm /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000 \
    -lm /home/kermit/programi/sphinx/cro-an/etc/cro-an.lm.DMP \
    -dict /home/kermit/programi/sphinx/cro-an/etc/cro-an.dic

Current configuration:
[NAME]      [DEFLT]     [VALUE]
-agc        none        none
-agcthresh  2.0     2.000000e+00
-alpha      0.97        9.700000e-01
-ascale     20.0        2.000000e+01
-backtrace  no      no
-beam       1e-48       1.000000e-48
-bestpath   yes     yes
-bestpathlw 9.5     9.500000e+00
-bghist     no      no
-ceplen     13      13
-cmn        current     current
-cmninit    8.0     8.0
-compallsen no      no
-debug              0
-dict               /home/kermit/programi/sphinx/cro-an/etc/cro-an.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-64
-fwdflatefwid   4       4
-fwdflatlw  8.5     8.500000e+00
-fwdflatsfwin   25      25
-fwdflatwbeam   7e-29       7.000000e-29
-fwdtree    yes     yes
-hmm                /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000
-input_endian   little      little
-jsgf               
-kdmaxbbi   -1      -1
-kdmaxdepth 0       0
-kdtree             
-latsize    5000        5000
-lda                
-ldadim     0       0
-lextreedump    0       0
-lifter     0       0
-lm             /home/kermit/programi/sphinx/cro-an/etc/cro-an.lm.DMP
-lmctl              
-lmname     default     default
-logbase    1.0001      1.000100e+00
-logfn              
-logspec    no      no
-lowerf     133.33334   1.333333e+02
-lpbeam     1e-40       1.000000e-40
-lponlybeam 7e-29       7.000000e-29
-lw     6.5     6.500000e+00
-maxhmmpf   -1      -1
-maxnewoov  20      20
-maxwpf     -1      -1
-mdef               
-mean               
-mfclogdir          
-mixw               
-mixwfloor  0.0000001   1.000000e-07
-mllr               
-mmap       yes     yes
-ncep       13      13
-nfft       512     512
-nfilt      40      40
-nwpen      1.0     1.000000e+00
-pbeam      1e-48       1.000000e-48
-pip        1.0     1.000000e+00
-pl_beam    1e-10       1.000000e-10
-pl_pbeam   1e-5        1.000000e-05
-pl_window  0       0
-rawlogdir          
-remove_dc  no      no
-round_filters  yes     yes
-samprate   16000       1.600000e+04
-seed       -1      -1
-sendump            
-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      legacy
-unit_area  yes     yes
-upperf     6855.4976   6.855498e+03
-usewdphones    no      no
-uw     1.0     1.000000e+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       7.000000e-29
-wip        0.65        6.500000e-01
-wlen       0.025625    2.562500e-02

INFO: cmd_ln.c(512): Parsing command line:
\
    -alpha 0.97 \
    -dither yes \
    -doublebw no \
    -nfilt 40 \
    -ncep 13 \
    -lowerf 133.33334 \
    -upperf 6855.4976 \
    -nfft 512 \
    -wlen 0.0256 \
    -transform legacy \
    -feat 1s_c_d_dd \
    -agc none \
    -cmn current \
    -varnorm no

Current configuration:
[NAME]      [DEFLT]     [VALUE]
-agc        none        none
-agcthresh  2.0     2.000000e+00
-alpha      0.97        9.700000e-01
-ceplen     13      13
-cmn        current     current
-cmninit    8.0     8.0
-dither     no      yes
-doublebw   no      no
-feat       1s_c_d_dd   1s_c_d_dd
-frate      100     100
-input_endian   little      little
-lda                
-ldadim     0       0
-lifter     0       0
-logspec    no      no
-lowerf     133.33334   1.333333e+02
-ncep       13      13
-nfft       512     512
-nfilt      40      40
-remove_dc  no      no
-round_filters  yes     yes
-samprate   16000       1.600000e+04
-seed       -1      -1
-smoothspec no      no
-svspec             
-transform  legacy      legacy
-unit_area  yes     yes
-upperf     6855.4976   6.855498e+03
-varnorm    no      no
-verbose    no      no
-warp_params            
-warp_type  inverse_linear  inverse_linear
-wlen       0.025625    2.560000e-02

INFO: acmod.c(238): Parsed model-specific feature parameters from /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/feat.params
INFO: fe_interface.c(288): You are using the internal mechanism to generate the seed.
INFO: feat.c(848): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: mdef.c(520): Reading model definition: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/mdef
INFO: bin_mdef.c(173): Allocating 25282 * 8 bytes (197 KiB) for CD tree
INFO: tmat.c(205): Reading HMM transition probability matrices: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/means
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/variances
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(356): 175292 variance values floored
INFO: acmod.c(119): Attempting to use PTHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/means
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/variances
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(356): 175292 variance values floored
ERROR: "ptm_mgau.c", line 801: Number of codebooks exceeds 256: 969
INFO: acmod.c(121): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/means
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/variances
INFO: ms_gauden.c(292): 969 codebook, 1 feature, size
 8x39
INFO: ms_gauden.c(356): 175292 variance values floored
INFO: ms_senone.c(160): Reading senone mixture weights: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/mixture_weights
INFO: ms_senone.c(211): Truncating senone logs3(pdf) values by 10 bits
INFO: ms_senone.c(218): Not transposing mixture weights in memory
INFO: ms_senone.c(277): Read mixture weights for 969 senones: 1 features x 8 codewords
INFO: ms_senone.c(331): Mapping senones to individual codebooks
INFO: ms_mgau.c(123): The value of topn: 4
INFO: dict.c(294): Allocating 4137 * 32 bytes (129 KiB) for word entries
INFO: dict.c(306): Reading main dictionary: /home/kermit/programi/sphinx/cro-an/etc/cro-an.dic
INFO: dict.c(206): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(309): 38 words read
INFO: dict.c(314): Reading filler dictionary: /home/kermit/programi/sphinx/cro-an/model_parameters/cro-an.cd_cont_1000/noisedict
INFO: dict.c(206): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(317): 3 words read
INFO: dict2pid.c(402): Building PID tables for dictionary
INFO: dict2pid.c(409): Allocating 41 * 8 bytes (0 KiB) for word-internal arrays
INFO: dict2pid.c(414): Allocating 29^3 * 2 bytes (47 KiB) for word-initial triphones
INFO: dict2pid.c(453): Allocating 22 entries of 2 bytes (0 KiB) for internal ssids
INFO: dict2pid.c(130): Allocated 20416 bytes (19 KiB) for word-final triphones
INFO: dict2pid.c(193): Allocated 20416 bytes (19 KiB) for single-phone word triphones
ERROR: "ngram_model_arpa.c", line 76: No \data\ mark in LM file
INFO: ngram_model_dmp.c(141): Will use memory-mapped I/O for LM file
INFO: ngram_model_dmp.c(195): ngrams 1=40, 2=230, 3=378
INFO: ngram_model_dmp.c(241):       40 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(289):      230 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314):      378 = LM.trigrams read
INFO: ngram_model_dmp.c(338):       44 = LM.prob2 entries read
INFO: ngram_model_dmp.c(357):       93 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(377):       29 = LM.prob3 entries read
INFO: ngram_model_dmp.c(405):        1 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(461):       40 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 10 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 32 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 32 single-phone words
INFO: ngram_search_fwdtree.c(324): after: max nonroot chan increased to 150
INFO: ngram_search_fwdtree.c(333): after: 10 root, 22 non-root channels, 31 single-phone words
INFO: ngram_search_fwdflat.c(153): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: cmn.c(175): CMN: 10.58 -0.40 -0.40 -0.41 -0.35  0.00 -0.12  0.01 -0.04 -0.03 -0.21 -0.03 -0.14 
INFO: ngram_search_fwdtree.c(1502):      825 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1504):    32059 senones evaluated (114/fr)
INFO: ngram_search_fwdtree.c(1506):    11278 channels searched (40/fr), 2760 1st, 8518 last
INFO: ngram_search_fwdtree.c(1510):     8518 words for which last channels evaluated (30/fr)
INFO: ngram_search_fwdtree.c(1513):        0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdflat.c(295): Utterance vocabulary contains 1 words
INFO: ngram_search_fwdflat.c(912):      493 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(914):      837 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(916):      631 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(918):      631 words searched (2/fr)
INFO: ngram_search_fwdflat.c(920):       39 word transitions (0/fr)
INFO: ngram_search.c(1137): lattice start node <s>.0 end node </s>.264
INFO: ps_lattice.c(1228): Normalizer P(O) = alpha(</s>:264:278) = -85594
INFO: ps_lattice.c(1266): Joint P(O,S) = -85594 P(S|O) = 0
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

Nickolay V. Shmyrev - 2011-05-23

Hello

If database decoder can produces the results while pocketsphinx_continuous
doesn't it means that the features for training were not extracted correctly.
Feature extraction parameters are configured in the file etc/feat.params. You
can learn more about that by reading the tutorial

http://cmusphinx.sourceforge.net/wiki/tutorialam#configure_sound_feature_para
meters

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Dražen Lučanin - 2011-05-23

OK, thanks for the advice. I'll take a look at that part.

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Using a Pocketsphinx model

Speech Recognition Toolkit

Forums

Help

Using a Pocketsphinx model document.SUBSCRIPTION_OPTIONS = { "thing": "topic", "subscribed": false, "url": "subscribe", "icon": { "css": "fa fa-envelope-o" } };

Using a Pocketsphinx model