I use 5 raw files as input. I have create them with arecord -t raw -f S16_LE
-c 1 -r 8000 -D default > ... or arecord -t raw -f S16_LE -c 1 -r 16000 -D
default > ... (I tried both 16 and 8k HZ)
The output file see like:
(kelen -1159)
(synowiec -994)
(turno -1119)
(weinberg -1104)
(cerdeiro -1053)
which are some names to detect + the word turno to try to detect one word
which was originally on the dictionary.
So for no of the raw files the sphinx is recognising anything. :(
-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 ../voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/feature_transform
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 2.000000e+02
-ncep 13 13
-nfft 512 512
-nfilt 40 32
-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 3.500000e+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.560000e-02
INFO: acmod.c(242): Parsed model-specific feature parameters from ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/feat.params
INFO: fe_interface.c(289): You are using the internal mechanism to generate
the seed.
INFO: feat.c(684): Initializing feature stream to type: '1s_c_d_dd',
ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean= 12.00, mean= 0.0
INFO: acmod.c(153): Reading linear feature transformation from ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/feature_transform
INFO: mdef.c(520): Reading model definition: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/mdef
INFO: bin_mdef.c(173): Allocating 28277 * 8 bytes (220 KiB) for CD tree
INFO: tmat.c(205): Reading HMM transition probability matrices: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/means
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/variances
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(354): 127 variance values floored
INFO: acmod.c(119): Attempting to use PTHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/means
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/variances
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(354): 127 variance values floored
INFO: ptm_mgau.c(800): Number of codebooks exceeds 256: 1578
INFO: acmod.c(121): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/means
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/variances
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(354): 127 variance values floored
INFO: ms_senone.c(160): Reading senone mixture weights: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/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 1578 senones: 1 features x 8
codewords
INFO: ms_senone.c(331): Mapping senones to individual codebooks
INFO: ms_mgau.c(122): The value of topn: 4
INFO: dict.c(306): Allocating 26762 * 32 bytes (836 KiB) for word entries
INFO: dict.c(321): Reading main dictionary: ../voxforge-
es-0.1.1/etc/voxforge_es_sphinx.dic
INFO: dict.c(212): Allocated 185 KiB for strings, 356 KiB for phones
INFO: dict.c(324): 22663 words read
INFO: dict.c(330): Reading filler dictionary: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/noisedict
INFO: dict.c(212): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(333): 3 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(404): Allocating 26^3 * 2 bytes (34 KiB) for word-initial
triphones
INFO: dict2pid.c(131): Allocated 16432 bytes (16 KiB) for word-final triphones
INFO: dict2pid.c(195): Allocated 16432 bytes (16 KiB) for single-phone word
triphones
INFO: ngram_model_arpa.c(477): ngrams 1=8, 2=12, 3=16
INFO: ngram_model_arpa.c(135): Reading unigrams
INFO: ngram_model_arpa.c(516): 8 = #unigrams created
INFO: ngram_model_arpa.c(195): Reading bigrams
INFO: ngram_model_arpa.c(533): 12 = #bigrams created
INFO: ngram_model_arpa.c(534): 4 = #prob2 entries
INFO: ngram_model_arpa.c(542): 5 = #bo_wt2 entries
INFO: ngram_model_arpa.c(292): Reading trigrams
INFO: ngram_model_arpa.c(555): 16 = #trigrams created
INFO: ngram_model_arpa.c(556): 3 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 234 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 37 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, 37
single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 128
ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has
pronunciation in the dictionary
INFO: ngram_search_fwdtree.c(338): after: 0 root, 0 non-root channels, 3
single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: cmn.c(175): CMN: 8.48 -0.29 0.15 0.01 -0.30 -0.40 -0.10 -0.15 -0.03
-0.04 -0.00 -0.12 -0.11
INFO: ngram_search_fwdtree.c(1549): 360 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 369 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 366 channels searched (2/fr), 0 1st, 366
last
INFO: ngram_search_fwdtree.c(1557): 366 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 277 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 567 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 567 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node .0 end node .48
INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 9 nodes, 9 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:48:123) = -76534
INFO: ps_lattice.c(1390): Joint P(O,S) = -76534 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): kelen: 1.24 seconds speech, 0.00 seconds CPU, 0.00 seconds
wall
INFO: batch.c(762): kelen: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 8.89 -0.20 0.28 -0.18 -0.35 -0.24 -0.10 -0.18 0.04
-0.11 -0.04 -0.13 -0.14
INFO: ngram_search_fwdtree.c(1549): 357 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 366 channels searched (2/fr), 0 1st, 366
last
INFO: ngram_search_fwdtree.c(1557): 366 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 324 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(942): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 569 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 569 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node .0 end node .47
INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 4 nodes, 3 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:47:123) = -68035
INFO: ps_lattice.c(1390): Joint P(O,S) = -68035 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): synowiec: 1.24 seconds speech, 0.00 seconds CPU, 0.00
seconds wall
INFO: batch.c(762): synowiec: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 8.53 0.14 -0.00 -0.38 -0.25 -0.14 -0.19 -0.14 -0.08
-0.01 -0.03 -0.13 -0.10
INFO: ngram_search_fwdtree.c(1549): 360 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 366 channels searched (2/fr), 0 1st, 366
last
INFO: ngram_search_fwdtree.c(1557): 366 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 282 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 567 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 567 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node .0 end node .48
INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 7 nodes, 7 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:48:123) = -73871
INFO: ps_lattice.c(1390): Joint P(O,S) = -73871 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): turno: 1.24 seconds speech, 0.00 seconds CPU, 0.00 seconds
wall
INFO: batch.c(762): turno: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 8.62 -0.14 0.04 -0.12 -0.34 -0.36 -0.17 -0.14 0.09
-0.04 0.02 -0.07 -0.11
INFO: ngram_search_fwdtree.c(1549): 390 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 402 channels searched (2/fr), 0 1st, 402
last
INFO: ngram_search_fwdtree.c(1557): 402 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.01 CPU 0.007 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 285 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 621 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 621 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node .0 end node .51
INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 5 nodes, 3 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:51:135) = -73462
INFO: ps_lattice.c(1390): Joint P(O,S) = -73462 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): weinberg: 1.36 seconds speech, 0.01 seconds CPU, 0.00
seconds wall
INFO: batch.c(762): weinberg: 0.01 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 9.04 -0.36 -0.06 -0.06 -0.16 -0.10 -0.09 -0.16 -0.09
-0.17 -0.07 -0.16 -0.12
INFO: ngram_search_fwdtree.c(1549): 394 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 402 channels searched (2/fr), 0 1st, 402
last
INFO: ngram_search_fwdtree.c(1557): 402 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 292 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 627 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 627 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node .0 end node .48
INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 7 nodes, 5 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:48:135) = -70902
INFO: ps_lattice.c(1390): Joint P(O,S) = -70902 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): cerdeiro: 1.36 seconds speech, 0.00 seconds CPU, 0.00
seconds wall
INFO: batch.c(762): cerdeiro: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: batch.c(774): TOTAL 6.44 seconds speech, 0.01 seconds CPU, 0.02 seconds
wall
INFO: batch.c(776): AVERAGE 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.01 CPU 0.002 xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 0.02 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(174): TOTAL fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(177): TOTAL fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(317): TOTAL bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 wall 0.000 xRT
cerdeiro@MacDesktop:~/speechreco$
I also tried as you see here with the default dictionary... same results.
I have one error which I tried to googled without results:
ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has
pronunciation in the dictionary
The rest seems to be ok but I always have:
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
what I guess is the problem, right?
I also tried to recognise words from the dictionary, but with the same
result...
I tried to run the ./scripts/build.sh from the voxforge-es-0.1.1 but I had to
patch it everywhere to work and I am still missing the file make_feats.pl
Thanks
Mariano.-
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi, I am trying to use pocketsphinx_batch to recognise names in Spanish. I
need a list of 40 names to be recognised.
I have downloaded the voxforge-es-0.1.1 packet, I have create a dictionary
with 5 names and a lm file with this 5 words too.
I run the command as follows:
pocketsphinx_batch -hmm ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500 -dict mydic.dic -lm
myarpa.arpa -adcin yes -ctl ctl.txt -cepext .raw -cepdir . -hyp result.txt
-bestpath yes
I use 5 raw files as input. I have create them with arecord -t raw -f S16_LE
-c 1 -r 8000 -D default > ... or arecord -t raw -f S16_LE -c 1 -r 16000 -D
default > ... (I tried both 16 and 8k HZ)
The output file see like:
(kelen -1159)
(synowiec -994)
(turno -1119)
(weinberg -1104)
(cerdeiro -1053)
which are some names to detect + the word turno to try to detect one word
which was originally on the dictionary.
So for no of the raw files the sphinx is recognising anything. :(
The output of the command line see like:
cerdeiro@MacDesktop:~/speechreco$ pocketsphinx_batch -hmm ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500 -dict ../voxforge-
es-0.1.1/etc/voxforge_es_sphinx.dic -lm myarpa.arpa -adcin yes -ctl ctl.txt
-cepext .raw -cepdir . -hyp result.txt
INFO: cmd_ln.c(691): Parsing command line:
pocketsphinx_batch \
-hmm ../voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500 \
-dict ../voxforge-es-0.1.1/etc/voxforge_es_sphinx.dic \
-lm myarpa.arpa \
-adcin yes \
-ctl ctl.txt \
-cepext .raw \
-cepdir . \
-hyp result.txt
Current configuration:
-adchdr 0 0
-adcin no yes
-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
-build_outdirs yes yes
-cepdir .
-cepext .mfc .raw
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-ctl ctl.txt
-ctlcount -1 -1
-ctlincr 1 1
-ctloffset 0 0
-ctm
-debug 0
-dict ../voxforge-es-0.1.1/etc/voxforge_es_sphinx.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
-fsgctl
-fsgdir
-fsgext
-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 ../voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500
-hyp result.txt
-hypseg
-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 myarpa.arpa
-lmctl
-lmname default default
-lmnamectl
-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
-mllrctl
-mllrdir
-mllrext
-mmap yes yes
-nbest 0 0
-nbestdir
-nbestext .hyp .hyp
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-nwpen 1.0 1.000000e+00
-outlatbeam 1e-5 1.000000e-05
-outlatdir
-outlatext .lat .lat
-outlatfmt s3 s3
-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
-senin no no
-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 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:
\
-alpha 0.97 \
-dither yes \
-doublebw no \
-nfilt 32 \
-ncep 13 \
-lowerf 200 \
-upperf 3500 \
-nfft 512 \
-wlen 0.0256 \
-transform legacy \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-varnorm no
Current configuration:
-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 ../voxforge-es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/feature_transform
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 2.000000e+02
-ncep 13 13
-nfft 512 512
-nfilt 40 32
-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 3.500000e+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.560000e-02
INFO: acmod.c(242): Parsed model-specific feature parameters from ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/feat.params
INFO: fe_interface.c(289): You are using the internal mechanism to generate
the seed.
INFO: feat.c(684): Initializing feature stream to type: '1s_c_d_dd',
ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean= 12.00, mean= 0.0
INFO: acmod.c(153): Reading linear feature transformation from ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/feature_transform
INFO: mdef.c(520): Reading model definition: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/mdef
INFO: bin_mdef.c(173): Allocating 28277 * 8 bytes (220 KiB) for CD tree
INFO: tmat.c(205): Reading HMM transition probability matrices: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/means
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/variances
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(354): 127 variance values floored
INFO: acmod.c(119): Attempting to use PTHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/means
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/variances
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(354): 127 variance values floored
INFO: ptm_mgau.c(800): Number of codebooks exceeds 256: 1578
INFO: acmod.c(121): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/means
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/variances
INFO: ms_gauden.c(292): 1578 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x29
INFO: ms_gauden.c(354): 127 variance values floored
INFO: ms_senone.c(160): Reading senone mixture weights: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/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 1578 senones: 1 features x 8
codewords
INFO: ms_senone.c(331): Mapping senones to individual codebooks
INFO: ms_mgau.c(122): The value of topn: 4
INFO: dict.c(306): Allocating 26762 * 32 bytes (836 KiB) for word entries
INFO: dict.c(321): Reading main dictionary: ../voxforge-
es-0.1.1/etc/voxforge_es_sphinx.dic
INFO: dict.c(212): Allocated 185 KiB for strings, 356 KiB for phones
INFO: dict.c(324): 22663 words read
INFO: dict.c(330): Reading filler dictionary: ../voxforge-
es-0.1.1/model_parameters/voxforge_es_sphinx.cd_cont_1500/noisedict
INFO: dict.c(212): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(333): 3 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(404): Allocating 26^3 * 2 bytes (34 KiB) for word-initial
triphones
INFO: dict2pid.c(131): Allocated 16432 bytes (16 KiB) for word-final triphones
INFO: dict2pid.c(195): Allocated 16432 bytes (16 KiB) for single-phone word
triphones
INFO: ngram_model_arpa.c(477): ngrams 1=8, 2=12, 3=16
INFO: ngram_model_arpa.c(135): Reading unigrams
INFO: ngram_model_arpa.c(516): 8 = #unigrams created
INFO: ngram_model_arpa.c(195): Reading bigrams
INFO: ngram_model_arpa.c(533): 12 = #bigrams created
INFO: ngram_model_arpa.c(534): 4 = #prob2 entries
INFO: ngram_model_arpa.c(542): 5 = #bo_wt2 entries
INFO: ngram_model_arpa.c(292): Reading trigrams
INFO: ngram_model_arpa.c(555): 16 = #trigrams created
INFO: ngram_model_arpa.c(556): 3 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 234 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 37 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, 37
single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 128
ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has
pronunciation in the dictionary
INFO: ngram_search_fwdtree.c(338): after: 0 root, 0 non-root channels, 3
single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: cmn.c(175): CMN: 8.48 -0.29 0.15 0.01 -0.30 -0.40 -0.10 -0.15 -0.03
-0.04 -0.00 -0.12 -0.11
INFO: ngram_search_fwdtree.c(1549): 360 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 369 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 366 channels searched (2/fr), 0 1st, 366
last
INFO: ngram_search_fwdtree.c(1557): 366 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 277 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 567 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 567 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node
.0 end node.48INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 9 nodes, 9 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:48:123) = -76534
INFO: ps_lattice.c(1390): Joint P(O,S) = -76534 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): kelen: 1.24 seconds speech, 0.00 seconds CPU, 0.00 seconds
wall
INFO: batch.c(762): kelen: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 8.89 -0.20 0.28 -0.18 -0.35 -0.24 -0.10 -0.18 0.04
-0.11 -0.04 -0.13 -0.14
INFO: ngram_search_fwdtree.c(1549): 357 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 366 channels searched (2/fr), 0 1st, 366
last
INFO: ngram_search_fwdtree.c(1557): 366 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 324 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(942): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 569 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 569 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node
.0 end node.47INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 4 nodes, 3 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:47:123) = -68035
INFO: ps_lattice.c(1390): Joint P(O,S) = -68035 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): synowiec: 1.24 seconds speech, 0.00 seconds CPU, 0.00
seconds wall
INFO: batch.c(762): synowiec: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 8.53 0.14 -0.00 -0.38 -0.25 -0.14 -0.19 -0.14 -0.08
-0.01 -0.03 -0.13 -0.10
INFO: ngram_search_fwdtree.c(1549): 360 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 366 channels searched (2/fr), 0 1st, 366
last
INFO: ngram_search_fwdtree.c(1557): 366 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 282 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 372 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 567 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 567 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node
.0 end node.48INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 7 nodes, 7 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:48:123) = -73871
INFO: ps_lattice.c(1390): Joint P(O,S) = -73871 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): turno: 1.24 seconds speech, 0.00 seconds CPU, 0.00 seconds
wall
INFO: batch.c(762): turno: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 8.62 -0.14 0.04 -0.12 -0.34 -0.36 -0.17 -0.14 0.09
-0.04 0.02 -0.07 -0.11
INFO: ngram_search_fwdtree.c(1549): 390 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 402 channels searched (2/fr), 0 1st, 402
last
INFO: ngram_search_fwdtree.c(1557): 402 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.01 CPU 0.007 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 285 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 621 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 621 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node
.0 end node.51INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 5 nodes, 3 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:51:135) = -73462
INFO: ps_lattice.c(1390): Joint P(O,S) = -73462 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): weinberg: 1.36 seconds speech, 0.01 seconds CPU, 0.00
seconds wall
INFO: batch.c(762): weinberg: 0.01 xRT (CPU), 0.00 xRT (elapsed)
INFO: cmn.c(175): CMN: 9.04 -0.36 -0.06 -0.06 -0.16 -0.10 -0.09 -0.16 -0.09
-0.17 -0.07 -0.16 -0.12
INFO: ngram_search_fwdtree.c(1549): 394 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1551): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1553): 402 channels searched (2/fr), 0 1st, 402
last
INFO: ngram_search_fwdtree.c(1557): 402 words for which last channels
evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.00 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(305): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(940): 292 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(942): 408 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(944): 627 channels searched (4/fr)
INFO: ngram_search_fwdflat.c(946): 627 words searched (4/fr)
INFO: ngram_search_fwdflat.c(948): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(954): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1253): lattice start node
.0 end node.48INFO: ngram_search.c(1281): Eliminated 0 nodes before end node
INFO: ngram_search.c(1386): Lattice has 7 nodes, 5 links
INFO: ps_lattice.c(1352): Normalizer P(O) = alpha(:48:135) = -70902
INFO: ps_lattice.c(1390): Joint P(O,S) = -70902 P(S|O) = 0
INFO: ngram_search.c(875): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(878): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): cerdeiro: 1.36 seconds speech, 0.00 seconds CPU, 0.00
seconds wall
INFO: batch.c(762): cerdeiro: 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: batch.c(774): TOTAL 6.44 seconds speech, 0.01 seconds CPU, 0.02 seconds
wall
INFO: batch.c(776): AVERAGE 0.00 xRT (CPU), 0.00 xRT (elapsed)
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.01 CPU 0.002 xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 0.02 wall 0.003 xRT
INFO: ngram_search_fwdflat.c(174): TOTAL fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(177): TOTAL fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(317): TOTAL bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 wall 0.000 xRT
cerdeiro@MacDesktop:~/speechreco$
I also tried as you see here with the default dictionary... same results.
I have one error which I tried to googled without results:
ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has
pronunciation in the dictionary
The rest seems to be ok but I always have:
INFO: ngram_search_fwdtree.c(1560): 0 candidate words for entering last phone
(0/fr)
what I guess is the problem, right?
I also tried to recognise words from the dictionary, but with the same
result...
I tried to run the ./scripts/build.sh from the voxforge-es-0.1.1 but I had to
patch it everywhere to work and I am still missing the file make_feats.pl
Thanks
Mariano.-
You need to write JSGF grammar. See
http://cmusphinx.sourceforge.net/wiki/tutoriallm
You can use it with -jsgf option
You need to add -samprate 8000 if your audio is 8khz
You need to make sure that cases match. I.e. words need to be all in
lowercase.
Thanks a LOT!!! it was an issue on the grammar. now is working perfect :)