Hello :
I am new with sphinx-4 and I follow the tutorial on Adapting the default acoustic model :
but the word_align.pl , I can't run it . in the same path where do i need to run this script.
when I run this
pocketsphinx_batch \
-adcin yes \
-cepdir wav \
-cepext .wav \
-ctl adaptation-test.fileids \
-lm <your.lm> \
-dict <your.dic, for="" example="" arctic.dic=""> \
-hmm <your_new_adapted_model, for="" example="" hub4wsj_sc_8kadapt=""> \
-hyp adapation-test.hyp
I get some information in the screen without the test result , and when I add the word_align.pl , I get error like word_align.pl not recognized .
please somebody help me .
thanks in advance. </your_new_adapted_model,></your.dic,></your.lm>
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I working with windows and I don't if i miss somthing or no ,this the result from the in the screen
pocketsphinx_batch \
-adcin yes \
-cepdir wav \
-cepext .wav \
-ctl adaptation-test.fileids \
-lm <your.lm> \
-dict <your.dic, for="" example="" arctic.dic=""> \
-hmm <your_new_adapted_model, for="" example="" hub4wsj_sc_8kadapt=""> \</your_new_adapted_model,></your.dic,></your.lm>
-varfloor 0.0001 1.000000e-004
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-029
-wip 0.65 6.500000e-001
-wlen 0.025625 2.562500e-002
I working with windows and I don't if i miss somthing or no ,this the result from the in the screen
pocketsphinx_batch \
-adcin yes \
-cepdir wav \
-cepext .wav \
-ctl adaptation-test.fileids \
-lm <your.lm> \
-dict <your.dic, for="" example="" arctic.dic=""> \
-hmm <your_new_adapted_model, for="" example="" hub4wsj_sc_8kadapt=""> \</your_new_adapted_model,></your.dic,></your.lm>
-varfloor 0.0001 1.000000e-004
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-029
-wip 0.65 6.500000e-001
-wlen 0.025625 2.562500e-002
Thanks Alexander ,
I would like to ask you about the script word_align.pl because it does not run with me , and about the result in the file adaptation-test.hyp it is like this
OPEN BROWSER (test1 -35601)
CLOSE BROWSER (test2 -33622)
GO OPEN (test3 -32105)
GO FACEBOOK (test4 -31124)
GO YOUTUBE (test5 -31801)
GO NISTOR WEBSITE (test6 -37833)
GO TORVERGAHTA GO WEBSITE (test7 -47294)
these are my words in my dictionary so what I miss .
could you help me more please
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
It's in "test" or "regression" directory. You also need to provide a
reference transcription in the form "<transcription> (<id>)".</id></transcription>
Thanks Alexander ,
I would like to ask you about the script word_align.pl because it does not run with me , and about the result in the file adaptation-test.hyp it is like this
OPEN BROWSER (test1 -35601)
CLOSE BROWSER (test2 -33622)
GO OPEN (test3 -32105)
GO FACEBOOK (test4 -31124)
GO YOUTUBE (test5 -31801)
GO NISTOR WEBSITE (test6 -37833)
GO TORVERGAHTA GO WEBSITE (test7 -47294)
these are my words in my dictionary so what I miss .
could you help me more please
Thanks Alexander ,
I put in my directory the transcription file . And all this without the script word_align.pl which will report me the extract error rate like said in the tutorial , so I think my problem is how can I run this script.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Sorry, but I don't quite get what you mean. The file is a PERL script,
so you obviously should run this way. Also, this question is asked
quite frequently, so it's worth to search on the forum.
Thanks Alexander ,
I put in my directory the transcription file . And all this without the script word_align.pl which will report me the extract error rate like said in the tutorial , so I think my problem is how can I run this script.
Hello :
I am new with sphinx-4 and I follow the tutorial on Adapting the default acoustic model :
but the word_align.pl , I can't run it . in the same path where do i need to run this script.
when I run this
pocketsphinx_batch \
-adcin yes \
-cepdir wav \
-cepext .wav \
-ctl adaptation-test.fileids \
-lm <your.lm> \
-dict <your.dic, for="" example="" arctic.dic=""> \
-hmm <your_new_adapted_model, for="" example="" hub4wsj_sc_8kadapt=""> \
-hyp adapation-test.hyp
I get some information in the screen without the test result , and when I add the word_align.pl , I get error like word_align.pl not recognized .
please somebody help me .
thanks in advance. </your_new_adapted_model,></your.dic,></your.lm>
I working with windows and I don't if i miss somthing or no ,this the result from the in the screen
pocketsphinx_batch \
-adcin yes \
-cepdir wav \
-cepext .wav \
-ctl adaptation-test.fileids \
-lm <your.lm> \
-dict <your.dic, for="" example="" arctic.dic=""> \
-hmm <your_new_adapted_model, for="" example="" hub4wsj_sc_8kadapt=""> \</your_new_adapted_model,></your.dic,></your.lm>
-varfloor 0.0001 1.000000e-004
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-029
-wip 0.65 6.500000e-001
-wlen 0.025625 2.562500e-002
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+000
-alpha 0.97 9.700000e-001
-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+000
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+004
-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+003
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-002
INFO: acmod.c(246): Parsed model-specific feature parameters from hub4wsj_sc_8kadapt/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: hub4wsj_sc_8kadapt/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: hub4wsj_sc_8kadapt/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: hub4wsj_sc_8kadapt/transition_matrices
INFO: acmod.c(121): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: hub4wsj_sc_8kadapt/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: hub4wsj_sc_8kadapt/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 hub4wsj_sc_8kadapt/sendump
INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(990): Rows: 256, Columns: 5150
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 4118 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: command.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 11 words read
INFO: dict.c(341): Reading filler dictionary: hub4wsj_sc_8kadapt/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(477): ngrams 1=12, 2=17, 3=15
INFO: ngram_model_arpa.c(135): Reading unigrams
INFO: ngram_model_arpa.c(516): 12 = #unigrams created
INFO: ngram_model_arpa.c(195): Reading bigrams
INFO: ngram_model_arpa.c(533): 17 = #bigrams created
INFO: ngram_model_arpa.c(534): 5 = #prob2 entries
INFO: ngram_model_arpa.c(542): 3 = #bo_wt2 entries
INFO: ngram_model_arpa.c(292): Reading trigrams
INFO: ngram_model_arpa.c(555): 15 = #trigrams created
INFO: ngram_model_arpa.c(556): 3 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 10 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 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, 12 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 163
INFO: ngram_search_fwdtree.c(338): after: 10 root, 35 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: cmn.c(175): CMN: 42.65 1.15 -1.74 -0.59 -0.47 -0.70 -0.77 -0.13 0.68 -0.49 -0.09 -0.17 -0.39
INFO: ngram_search_fwdtree.c(1549): 2654 words recognized (9/fr)
INFO: ngram_search_fwdtree.c(1551): 51660 senones evaluated (172/fr)
INFO: ngram_search_fwdtree.c(1553): 22904 channels searched (76/fr), 2840 1st, 14044 last
INFO: ngram_search_fwdtree.c(1557): 3401 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 575 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.02 CPU 0.005 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.02 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 9 words
INFO: ngram_search_fwdflat.c(937): 618 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 34968 senones evaluated (117/fr)
INFO: ngram_search_fwdflat.c(941): 18411 channels searched (61/fr)
INFO: ngram_search_fwdflat.c(943): 1272 words searched (4/fr)
INFO: ngram_search_fwdflat.c(945): 628 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.02 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.01 wall 0.005 xRT
INFO: ngram_search.c(1266): lattice start node
.0 end node.213INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 86 nodes, 43 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(:213:298) = -1842637
INFO: ps_lattice.c(1403): Joint P(O,S) = -1842887 P(S|O) = -250
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): test1: 2.99 seconds speech, 0.03 seconds CPU, 0.04 seconds wall
INFO: batch.c(762): test1: 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: cmn.c(175): CMN: 40.59 -0.24 -1.77 -0.92 -0.21 -0.82 -1.18 -0.19 0.67 -0.41 0.03 -0.26 -0.21
INFO: ngram_search_fwdtree.c(1549): 2372 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1551): 49601 senones evaluated (171/fr)
INFO: ngram_search_fwdtree.c(1553): 22413 channels searched (77/fr), 2664 1st, 13823 last
INFO: ngram_search_fwdtree.c(1557): 3257 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 540 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.02 CPU 0.005 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.02 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 9 words
INFO: ngram_search_fwdflat.c(937): 545 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 30355 senones evaluated (105/fr)
INFO: ngram_search_fwdflat.c(941): 16425 channels searched (56/fr)
INFO: ngram_search_fwdflat.c(943): 1119 words searched (3/fr)
INFO: ngram_search_fwdflat.c(945): 623 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.02 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.01 wall 0.004 xRT
INFO: ngram_search.c(1266): lattice start node
.0 end node.268INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 91 nodes, 40 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(:268:288) = -1740485
INFO: ps_lattice.c(1403): Joint P(O,S) = -1741560 P(S|O) = -1075
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): test2: 2.89 seconds speech, 0.03 seconds CPU, 0.04 seconds wall
INFO: batch.c(762): test2: 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: cmn.c(175): CMN: 38.02 0.44 -1.24 -1.09 -0.10 -1.06 -0.57 -1.02 0.85 -0.56 0.50 -0.44 -0.35
INFO: ngram_search_fwdtree.c(1549): 2309 words recognized (9/fr)
INFO: ngram_search_fwdtree.c(1551): 43645 senones evaluated (169/fr)
INFO: ngram_search_fwdtree.c(1553): 18889 channels searched (73/fr), 2539 1st, 10661 last
INFO: ngram_search_fwdtree.c(1557): 2968 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 614 candidate words for entering last phone (2/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.02 CPU 0.006 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.02 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(937): 543 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 27241 senones evaluated (106/fr)
INFO: ngram_search_fwdflat.c(941): 13469 channels searched (52/fr)
INFO: ngram_search_fwdflat.c(943): 885 words searched (3/fr)
INFO: ngram_search_fwdflat.c(945): 411 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.02 CPU 0.006 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.01 wall 0.005 xRT
INFO: ngram_search.c(1266): lattice start node
.0 end node.220INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 91 nodes, 56 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(:220:256) = -1685272
INFO: ps_lattice.c(1403): Joint P(O,S) = -1687201 P(S|O) = -1929
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): test3: 2.57 seconds speech, 0.03 seconds CPU, 0.04 seconds wall
INFO: batch.c(762): test3: 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: cmn.c(175): CMN: 37.27 -0.26 -1.57 -1.41 -0.16 -0.74 -0.59 -1.15 0.52 0.21 0.25 -0.51 -0.11
INFO: ngram_search_fwdtree.c(1549): 2257 words recognized (9/fr)
INFO: ngram_search_fwdtree.c(1551): 41941 senones evaluated (159/fr)
INFO: ngram_search_fwdtree.c(1553): 18663 channels searched (70/fr), 2451 1st, 11167 last
INFO: ngram_search_fwdtree.c(1557): 2889 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 551 candidate words for entering last phone (2/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.03 CPU 0.012 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.02 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(937): 457 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 18089 senones evaluated (69/fr)
INFO: ngram_search_fwdflat.c(941): 9022 channels searched (34/fr)
INFO: ngram_search_fwdflat.c(943): 806 words searched (3/fr)
INFO: ngram_search_fwdflat.c(945): 373 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.01 wall 0.004 xRT
INFO: ngram_search.c(1266): lattice start node
.0 end node.204INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 62 nodes, 30 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(:204:261) = -1613428
INFO: ps_lattice.c(1403): Joint P(O,S) = -1613667 P(S|O) = -239
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): test4: 2.62 seconds speech, 0.03 seconds CPU, 0.03 seconds wall
INFO: batch.c(762): test4: 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: cmn.c(175): CMN: 38.04 0.10 -1.10 -0.62 -0.09 -0.59 -1.08 -1.25 0.42 0.06 0.15 -0.35 -0.30
INFO: ngram_search_fwdtree.c(1549): 2172 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1551): 42275 senones evaluated (162/fr)
INFO: ngram_search_fwdtree.c(1553): 18690 channels searched (71/fr), 2461 1st, 10906 last
INFO: ngram_search_fwdtree.c(1557): 2906 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 537 candidate words for entering last phone (2/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.02 CPU 0.006 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.02 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 6 words
INFO: ngram_search_fwdflat.c(937): 498 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 18605 senones evaluated (71/fr)
INFO: ngram_search_fwdflat.c(941): 9401 channels searched (36/fr)
INFO: ngram_search_fwdflat.c(943): 860 words searched (3/fr)
INFO: ngram_search_fwdflat.c(945): 380 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.02 CPU 0.006 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.01 wall 0.004 xRT
INFO: ngram_search.c(1266): lattice start node
.0 end node.208INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 71 nodes, 37 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(:208:259) = -1648250
INFO: ps_lattice.c(1403): Joint P(O,S) = -1648330 P(S|O) = -80
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): test5: 2.60 seconds speech, 0.03 seconds CPU, 0.04 seconds wall
INFO: batch.c(762): test5: 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: cmn.c(175): CMN: 43.77 -1.90 -2.03 -0.62 -0.67 -1.07 -0.47 -0.77 0.75 -0.48 0.16 -0.41 -0.11
INFO: ngram_search_fwdtree.c(1549): 2454 words recognized (7/fr)
INFO: ngram_search_fwdtree.c(1551): 49917 senones evaluated (152/fr)
INFO: ngram_search_fwdtree.c(1553): 22600 channels searched (68/fr), 2860 1st, 14213 last
INFO: ngram_search_fwdtree.c(1557): 3430 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 501 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.03 CPU 0.009 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.02 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 7 words
INFO: ngram_search_fwdflat.c(937): 477 words recognized (1/fr)
INFO: ngram_search_fwdflat.c(939): 25228 senones evaluated (77/fr)
INFO: ngram_search_fwdflat.c(941): 13140 channels searched (39/fr)
INFO: ngram_search_fwdflat.c(943): 992 words searched (3/fr)
INFO: ngram_search_fwdflat.c(945): 461 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.02 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.01 wall 0.004 xRT
INFO: ngram_search.c(1266): lattice start node
.0 end node.282INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 68 nodes, 27 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(:282:327) = -1960328
INFO: ps_lattice.c(1403): Joint P(O,S) = -1960458 P(S|O) = -130
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): test6: 3.28 seconds speech, 0.05 seconds CPU, 0.04 seconds wall
INFO: batch.c(762): test6: 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: cmn.c(175): CMN: 47.90 -0.73 -1.66 -0.48 -0.64 -1.26 -0.68 -0.76 0.73 -0.78 0.23 -0.40 -0.17
INFO: ngram_search_fwdtree.c(1549): 3304 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1551): 70335 senones evaluated (175/fr)
INFO: ngram_search_fwdtree.c(1553): 32072 channels searched (79/fr), 3786 1st, 20608 last
INFO: ngram_search_fwdtree.c(1557): 4566 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 802 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.03 CPU 0.008 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.03 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 9 words
INFO: ngram_search_fwdflat.c(937): 753 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 41168 senones evaluated (102/fr)
INFO: ngram_search_fwdflat.c(941): 21378 channels searched (53/fr)
INFO: ngram_search_fwdflat.c(943): 1492 words searched (3/fr)
INFO: ngram_search_fwdflat.c(945): 633 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.02 CPU 0.004 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.02 wall 0.005 xRT
INFO: ngram_search.c(1266): lattice start node
.0 end node.326INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 117 nodes, 59 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(:326:401) = -2479016
INFO: ps_lattice.c(1403): Joint P(O,S) = -2481230 P(S|O) = -2214
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.000 xRT
INFO: batch.c(760): test7: 4.02 seconds speech, 0.05 seconds CPU, 0.05 seconds wall
INFO: batch.c(762): test7: 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: batch.c(774): TOTAL 20.97 seconds speech, 0.25 seconds CPU, 0.28 seconds wall
INFO: batch.c(776): AVERAGE 0.01 xRT (CPU), 0.01 xRT (elapsed)
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.16 CPU 0.007 xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 0.15 wall 0.007 xRT
INFO: ngram_search_fwdflat.c(174): TOTAL fwdflat 0.09 CPU 0.004 xRT
INFO: ngram_search_fwdflat.c(177): TOTAL fwdflat 0.09 wall 0.004 xRT
INFO: ngram_search.c(317): TOTAL bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.01 wall 0.000 xRT
-hyp adapation-test.hyp
The result is saved in adaptation-test.hyp - the file that you
provided along with -hyp option.
On Mon, Nov 24, 2014 at 8:11 PM, Afiha Musbah Omar
musbahafiha@users.sf.net wrote:
--
Sincerely, Alexander
Thanks Alexander ,
I would like to ask you about the script word_align.pl because it does not run with me , and about the result in the file adaptation-test.hyp it is like this
OPEN BROWSER (test1 -35601)
CLOSE BROWSER (test2 -33622)
GO OPEN (test3 -32105)
GO FACEBOOK (test4 -31124)
GO YOUTUBE (test5 -31801)
GO NISTOR WEBSITE (test6 -37833)
GO TORVERGAHTA GO WEBSITE (test7 -47294)
these are my words in my dictionary so what I miss .
could you help me more please
It's in "test" or "regression" directory. You also need to provide a
reference transcription in the form "<transcription> (<id>)".</id></transcription>
On Tue, Nov 25, 2014 at 2:52 AM, Afiha Musbah Omar
musbahafiha@users.sf.net wrote:
--
Sincerely, Alexander
Thanks Alexander ,
I put in my directory the transcription file . And all this without the script word_align.pl which will report me the extract error rate like said in the tutorial , so I think my problem is how can I run this script.
Sorry, but I don't quite get what you mean. The file is a PERL script,
so you obviously should run this way. Also, this question is asked
quite frequently, so it's worth to search on the forum.
On Tue, Nov 25, 2014 at 3:10 AM, Afiha Musbah Omar
musbahafiha@users.sf.net wrote:
--
Sincerely, Alexander