Click here to register.

Spanish

Flat
Spanish model does not work
User: samuel ynoa
Date: 4/3/2014 12:03 am
Views: 3931
Rating: 5

Bueno en primer lugar, lo siento por mi Inglés. 

Tengo un modelo acústico en español instalado y estoy tratando de usar utlizarlo pocketsphinx_continous pero cuando regrese palabras en Inglés y no en español. Necesito ayuda urgente. 

Acá les dejo un ejemplo de cómo he tratado de utilizar el pocketsphinx_continous.

pocketsphinx_continuous-mftt = 512-hmm / home/pi/Desktop/model_esp/voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500

pocketsphinx_continuous-mftt = 512-hmm / home/pi/Desktop/model_esp/voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500 /-lm voxforge_es_sphinx.transcription.test.lm-dict voxforge_es_sphinx_MX.dic
Re: Spanish model does not work
User: nsh
Date: 4/3/2014 2:49 am
Views: 289
Rating: 6

Proporcione la salida pocketsphinx completo por favor 

Re: Spanish model does not work
User: samuel ynoa
Date: 4/3/2014 10:57 pm
Views: 120
Rating: 5

While this is the case I want to make this recognition in Spanish by using the acoustic model VoxForge-es-0.1.1 but when I test with the resulting pocket_continouos pabras are in English. this case to mention the word 'hola' and the result was 'before long' is not what is happening or if I'm missing something.

 

pi@raspberrypi ~ $ pocketsphinx_continuous -mftt = 512 -hmm /home/pi/Desktop/model_esp/voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/ -lm voxforge_es_sphinx.transcription.test.lm -dict voxforge_es_sphinx_MX.dic

INFO: cmd_ln.c(691): Parsing command line:

pocketsphinx_continuous \

        -mftt = 512 \

        -hmm /home/pi/Desktop/model_esp/voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/ \

        -lm voxforge_es_sphinx.transcription.test.lm \

        -dict voxforge_es_sphinx_MX.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

-aw             1               1

-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

-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

-infile

-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

-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

-min_endfr      0               0

-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

-senlogdir

-senmgau

-silprob        0.005           5.000000e-03

-smoothspec     no              no

-svspec

-time           no              no

-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(691): Parsing command line:

\

        -nfilt 20 \

        -lowerf 1 \

        -upperf 4000 \

        -wlen 0.025 \

        -transform dct \

        -round_filters no \

        -remove_dc yes \

        -svspec 0-12/13-25/26-38 \

        -feat 1s_c_d_dd \

        -agc none \

        -cmn current \

        -cmninit 56,-3,1 \

        -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             56,-3,1

-dither         no              no

-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       1.000000e+00

-ncep           13              13

-nfft           512             512

-nfilt          40              20

-remove_dc      no              yes

-round_filters  yes             no

-samprate       16000           1.600000e+04

-seed           -1              -1

-smoothspec     no              no

-svspec                         0-12/13-25/26-38

-transform      legacy          dct

-unit_area      yes             yes

-upperf         6855.4976       4.000000e+03

-varnorm        no              no

-verbose        no              no

-warp_params

-warp_type      inverse_linear  inverse_linear

-wlen           0.025625        2.500000e-02

 

INFO: acmod.c(246): Parsed model-specific feature parameters from /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/feat.params

INFO: feat.c(713): 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: acmod.c(167): Using subvector specification 0-12/13-25/26-38

INFO: mdef.c(517): Reading model definition: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/mdef

INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef file

INFO: bin_mdef.c(336): Reading binary model definition: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/mdef

INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-sen, 5150 Sen, 27135 Sen-Seq

INFO: tmat.c(205): Reading HMM transition probability matrices: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices

INFO: acmod.c(121): Attempting to use SCHMM computation module

INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/means

INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/variances

INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(354): 0 variance values floored

INFO: s2_semi_mgau.c(903): Loading senones from dump file /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump

INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION

INFO: s2_semi_mgau.c(1022): Using memory-mapped I/O for senones

INFO: s2_semi_mgau.c(1296): Maximum top-N: 4 Top-N beams: 0 0 0

INFO: dict.c(317): Allocating 137543 * 20 bytes (2686 KiB) for word entries

INFO: dict.c(332): Reading main dictionary: /usr/local/share/pocketsphinx/model/lm/en_US/cmu07a.dic

INFO: dict.c(211): Allocated 1010 KiB for strings, 1664 KiB for phones

INFO: dict.c(335): 133436 words read

INFO: dict.c(341): Reading filler dictionary: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/noisedict

INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones

INFO: dict.c(344): 11 words read

INFO: dict2pid.c(396): Building PID tables for dictionary

INFO: dict2pid.c(404): Allocating 50^3 * 2 bytes (244 KiB) for word-initial triphones

INFO: dict2pid.c(131): Allocated 30200 bytes (29 KiB) for word-final triphones

INFO: dict2pid.c(195): Allocated 30200 bytes (29 KiB) for single-phone word triphones

INFO: ngram_model_arpa.c(77): No \data\ mark in LM file

INFO: ngram_model_dmp.c(142): Will use memory-mapped I/O for LM file

INFO: ngram_model_dmp.c(196): ngrams 1=5001, 2=436879, 3=418286

INFO: ngram_model_dmp.c(242):     5001 = LM.unigrams(+trailer) read

INFO: ngram_model_dmp.c(288):   436879 = LM.bigrams(+trailer) read

INFO: ngram_model_dmp.c(314):   418286 = LM.trigrams read

INFO: ngram_model_dmp.c(339):    37293 = LM.prob2 entries read

INFO: ngram_model_dmp.c(359):    14370 = LM.bo_wt2 entries read

INFO: ngram_model_dmp.c(379):    36094 = LM.prob3 entries read

INFO: ngram_model_dmp.c(407):      854 = LM.tseg_base entries read

INFO: ngram_model_dmp.c(463):     5001 = ascii word strings read

INFO: ngram_search_fwdtree.c(99): 788 unique initial diphones

INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 60 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, 60 single-phone words

INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 13428

INFO: ngram_search_fwdtree.c(338): after: 457 root, 13300 non-root channels, 26 single-phone words

INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25

INFO: continuous.c(371): pocketsphinx_continuous COMPILED ON: Nov 25 2013, AT: 03:17:56

 

Warning: Could not find Capture element

READY....

Listening...

Input overrun, read calls are too rare (non-fatal)

INFO: ngram_search.c(482): Resized score stack to 200000 entries

Input overrun, read calls are too rare (non-fatal)

INFO: ngram_search.c(474): Resized backpointer table to 10000 entries

Input overrun, read calls are too rare (non-fatal)

Input overrun, read calls are too rare (non-fatal)

Input overrun, read calls are too rare (non-fatal)

Recording is stopped, start recording with ad_start_rec

Stopped listening, please wait...

INFO: cmn_prior.c(121): cmn_prior_update: from < 56.00 -3.00  1.00  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   < 54.26  4.94 -1.64 -0.13 -0.22  0.14 -0.51 -0.26 -0.16  0.45 -0.59  0.12 -0.32 >

INFO: ngram_search_fwdtree.c(1549):     7516 words recognized (60/fr)

INFO: ngram_search_fwdtree.c(1551):   471572 senones evaluated (3773/fr)

INFO: ngram_search_fwdtree.c(1553):   937994 channels searched (7503/fr), 55297 1st, 184085 last

INFO: ngram_search_fwdtree.c(1557):    11932 words for which last channels evaluated (95/fr)

INFO: ngram_search_fwdtree.c(1560):   115617 candidate words for entering last phone (924/fr)

INFO: ngram_search_fwdtree.c(1562): fwdtree 8.73 CPU 6.984 xRT

INFO: ngram_search_fwdtree.c(1565): fwdtree 10.48 wall 8.387 xRT

INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 231 words

INFO: ngram_search_fwdflat.c(937):     4967 words recognized (40/fr)

INFO: ngram_search_fwdflat.c(939):   201657 senones evaluated (1613/fr)

INFO: ngram_search_fwdflat.c(941):   390033 channels searched (3120/fr)

INFO: ngram_search_fwdflat.c(943):    21993 words searched (175/fr)

INFO: ngram_search_fwdflat.c(945):    12348 word transitions (98/fr)

INFO: ngram_search_fwdflat.c(948): fwdflat 2.27 CPU 1.816 xRT

INFO: ngram_search_fwdflat.c(951): fwdflat 2.28 wall 1.822 xRT

INFO: ngram_search.c(1266): lattice start node <s>.0 end node </s>.111

INFO: ngram_search.c(1294): Eliminated 0 nodes before end node

INFO: ngram_search.c(1399): Lattice has 332 nodes, 3950 links

INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(</s>:111:123) = -940465

INFO: ps_lattice.c(1403): Joint P(O,S) = -966800 P(S|O) = -26335

INFO: ngram_search.c(888): bestpath 0.68 CPU 0.548 xRT

INFO: ngram_search.c(891): bestpath 0.69 wall 0.557 xRT

000000000: before long

READY...

Re: Spanish model does not work
User: nsh
Date: 4/4/2014 1:27 am
Views: 89
Rating: 4

The first argument should be

 -nfft 512

Note that it's nfft instead mfft, n instead of m. Also there is no equal sign. That = breaks things.

The final command line must be something like this:

pocketsphinx_continuous -nftt 512 \
-hmm /home/pi/Desktop/model_esp/voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500 \
-lm voxforge_es_sphinx.transcription.test.lm -dict voxforge_es_sphinx_MX.dic
Re: Spanish model does not work
User: samuel ynoa
Date: 4/4/2014 6:31 am
Views: 134
Rating: 6

hello I made the changes you suggested but the problem still nsh persists even now try running the program from the directory where the .dic and .lm are continuous files just speak Spanish and returns something in English. leave output pocketsphinx

I just said hello again

pi@raspberrypi ~/Desktop/model_esp/voxforge-es-0.1.1/etc $

 pocketsphinx_continuous -nftt 512\ -hmm /home/pi/Desktop/model_esp/voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/ -lm voxforge_es_sphinx.transcription.test.lm -dict voxforge_es_sphinx_MX.dic

 

INFO: cmd_ln.c(691): Parsing command line:

pocketsphinx_continuous \

        -nftt 512 -hmm /home/pi/Desktop/model_esp/voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/ \

        -lm voxforge_es_sphinx.transcription.test.lm \

        -dict voxforge_es_sphinx_MX.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

-aw             1               1

-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

-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

-infile

-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

-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

-min_endfr      0               0

-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

-senlogdir

-senmgau

-silprob        0.005           5.000000e-03

-smoothspec     no              no

-svspec

-time           no              no

-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(691): Parsing command line:

\

        -nfilt 20 \

        -lowerf 1 \

        -upperf 4000 \

        -wlen 0.025 \

        -transform dct \

        -round_filters no \

        -remove_dc yes \

        -svspec 0-12/13-25/26-38 \

        -feat 1s_c_d_dd \

        -agc none \

        -cmn current \

        -cmninit 56,-3,1 \

        -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             56,-3,1

-dither         no              no

-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       1.000000e+00

-ncep           13              13

-nfft           512             512

-nfilt          40              20

-remove_dc      no              yes

-round_filters  yes             no

-samprate       16000           1.600000e+04

-seed           -1              -1

-smoothspec     no              no

-svspec                         0-12/13-25/26-38

-transform      legacy          dct

-unit_area      yes             yes

-upperf         6855.4976       4.000000e+03

-varnorm        no              no

-verbose        no              no

-warp_params

-warp_type      inverse_linear  inverse_linear

-wlen           0.025625        2.500000e-02

 

INFO: acmod.c(246): Parsed model-specific feature parameters from /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/feat.params

INFO: feat.c(713): 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: acmod.c(167): Using subvector specification 0-12/13-25/26-38

INFO: mdef.c(517): Reading model definition: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/mdef

INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef file

INFO: bin_mdef.c(336): Reading binary model definition: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/mdef

INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-sen, 5150 Sen, 27135 Sen-Seq

INFO: tmat.c(205): Reading HMM transition probability matrices: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices

INFO: acmod.c(121): Attempting to use SCHMM computation module

INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/means

INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/variances

INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(294):  256x13

INFO: ms_gauden.c(354): 0 variance values floored

INFO: s2_semi_mgau.c(903): Loading senones from dump file /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump

INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION

INFO: s2_semi_mgau.c(1022): Using memory-mapped I/O for senones

INFO: s2_semi_mgau.c(1296): Maximum top-N: 4 Top-N beams: 0 0 0

INFO: dict.c(317): Allocating 137543 * 20 bytes (2686 KiB) for word entries

INFO: dict.c(332): Reading main dictionary: /usr/local/share/pocketsphinx/model/lm/en_US/cmu07a.dic

INFO: dict.c(211): Allocated 1010 KiB for strings, 1664 KiB for phones

INFO: dict.c(335): 133436 words read

INFO: dict.c(341): Reading filler dictionary: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/noisedict

INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones

INFO: dict.c(344): 11 words read

INFO: dict2pid.c(396): Building PID tables for dictionary

INFO: dict2pid.c(404): Allocating 50^3 * 2 bytes (244 KiB) for word-initial triphones

INFO: dict2pid.c(131): Allocated 30200 bytes (29 KiB) for word-final triphones

INFO: dict2pid.c(195): Allocated 30200 bytes (29 KiB) for single-phone word triphones

INFO: ngram_model_arpa.c(77): No \data\ mark in LM file

INFO: ngram_model_dmp.c(142): Will use memory-mapped I/O for LM file

INFO: ngram_model_dmp.c(196): ngrams 1=5001, 2=436879, 3=418286

INFO: ngram_model_dmp.c(242):     5001 = LM.unigrams(+trailer) read

INFO: ngram_model_dmp.c(288):   436879 = LM.bigrams(+trailer) read

INFO: ngram_model_dmp.c(314):   418286 = LM.trigrams read

INFO: ngram_model_dmp.c(339):    37293 = LM.prob2 entries read

INFO: ngram_model_dmp.c(359):    14370 = LM.bo_wt2 entries read

INFO: ngram_model_dmp.c(379):    36094 = LM.prob3 entries read

INFO: ngram_model_dmp.c(407):      854 = LM.tseg_base entries read

INFO: ngram_model_dmp.c(463):     5001 = ascii word strings read

INFO: ngram_search_fwdtree.c(99): 788 unique initial diphones

INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 60 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, 60 single-phone words

INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 13428

INFO: ngram_search_fwdtree.c(338): after: 457 root, 13300 non-root channels, 26 single-phone words

INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25

INFO: continuous.c(371): pocketsphinx_continuous COMPILED ON: Nov 25 2013, AT: 03:17:56

 

Warning: Could not find Capture element

READY....

Listening...

Input overrun, read calls are too rare (non-fatal)

Input overrun, read calls are too rare (non-fatal)

Input overrun, read calls are too rare (non-fatal)

Input overrun, read calls are too rare (non-fatal)

Input overrun, read calls are too rare (non-fatal)

INFO: ngram_search.c(474): Resized backpointer table to 10000 entries

INFO: ngram_search.c(482): Resized score stack to 200000 entries

Input overrun, read calls are too rare (non-fatal)

Recording is stopped, start recording with ad_start_rec

Stopped listening, please wait...

INFO: cmn_prior.c(121): cmn_prior_update: from < 56.00 -3.00  1.00  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   < 53.55  4.33 -1.52 -0.57 -0.65  0.07 -0.67 -0.13 -0.18  0.52 -0.54  0.15 -0.30 >

INFO: ngram_search_fwdtree.c(1549):     6674 words recognized (35/fr)

INFO: ngram_search_fwdtree.c(1551):   695526 senones evaluated (3661/fr)

INFO: ngram_search_fwdtree.c(1553):  1346281 channels searched (7085/fr), 84966 1st, 164631 last

INFO: ngram_search_fwdtree.c(1557):    11652 words for which last channels evaluated (61/fr)

INFO: ngram_search_fwdtree.c(1560):   195542 candidate words for entering last phone (1029/fr)

INFO: ngram_search_fwdtree.c(1562): fwdtree 12.46 CPU 6.558 xRT

INFO: ngram_search_fwdtree.c(1565): fwdtree 14.05 wall 7.396 xRT

INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 163 words

INFO: ngram_search_fwdflat.c(937):     2537 words recognized (13/fr)

INFO: ngram_search_fwdflat.c(939):   156656 senones evaluated (825/fr)

INFO: ngram_search_fwdflat.c(941):   222539 channels searched (1171/fr)

INFO: ngram_search_fwdflat.c(943):    14101 words searched (74/fr)

INFO: ngram_search_fwdflat.c(945):    10184 word transitions (53/fr)

INFO: ngram_search_fwdflat.c(948): fwdflat 1.20 CPU 0.632 xRT

INFO: ngram_search_fwdflat.c(951): fwdflat 1.20 wall 0.634 xRT

INFO: ngram_search.c(1214): </s> not found in last frame, using warner.188 instead

INFO: ngram_search.c(1266): lattice start node <s>.0 end node warner.2

INFO: ngram_search.c(1294): Eliminated 60 nodes before end node

INFO: ngram_search.c(1399): Lattice has 203 nodes, 1 links

INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(warner:2:188) = -1303774

INFO: ps_lattice.c(1403): Joint P(O,S) = -1303774 P(S|O) = 0

INFO: ngram_search.c(888): bestpath 0.01 CPU 0.005 xRT

INFO: ngram_search.c(891): bestpath 0.02 wall 0.009 xRT

000000000: warner

READY..

Re: Spanish model does not work
User: samuel ynoa
Date: 4/4/2014 10:13 pm
Views: 99
Rating: 4

already found the solution to the problem anyway thank you very much

Re: Spanish model does not work
User: nsh
Date: 4/5/2014 12:31 am
Views: 214
Rating: 7

So what was the problem and what was the solution?

 

Re: Spanish model does not work
User: samuel ynoa
Date: 4/9/2014 6:31 pm
Views: 1218
Rating: 6

Well the problem was exactly the same as you indicated me to change the value of ntff just that for some strange reason I did not work on the command line. so look for the file that contains it change the value from 256 to 512 and voila. I can not remember the file name but when I get home I'll find out and tell them. thanks for everything.

PreviousNext