Sphinx武林秘籍(下)
为什么80%的码农都做不了架构师?>>>
Sphinx武林秘籍(下)
――使用训练好的语言模型与声学模型
一、第一次使用
#cp -rf my_db.cd_cont_1000 /usr/local/bin
#cd ..
#cd etc
#cp my_db.dic my_db.lm.DMP /usr/local/bin/
#cd /usr/local/bin
# ./pocketsphinx_continuous -hmm my_db.cd_cont_1000 -lm my_db.lm.DMP -dict my_db.dic
INFO: cmd_ln.c(512): Parsing command line:
./pocketsphinx_continuous \
-hmm my_db.cd_cont_1000 \
-lm my_db.lm.DMP \
-dict my_db.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 my_db.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 my_db.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 my_db.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 my_db.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: my_db.cd_cont_1000/mdef
INFO: bin_mdef.c(173): Allocating 304 * 8 bytes (2 KiB) for CD tree
INFO: tmat.c(205): Reading HMM transition probability matrices: my_db.cd_cont_1000/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/means
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/variances
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(356): 30781 variance values floored
INFO: acmod.c(119): Attempting to use PTHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/means
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/variances
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(356): 30781 variance values floored
INFO: ptm_mgau.c(671): Reading mixture weights file 'my_db.cd_cont_1000/mixture_weights'
INFO: ptm_mgau.c(765): Read 105 x 1 x 8 mixture weights
INFO: ptm_mgau.c(831): Maximum top-N: 4
INFO: dict.c(294): Allocating 4112 * 20 bytes (80 KiB) for word entries
INFO: dict.c(306): Reading main dictionary: my_db.dic
INFO: dict.c(206): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(309): 13 words read
INFO: dict.c(314): Reading filler dictionary: my_db.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(396): Building PID tables for dictionary
INFO: dict2pid.c(405): Allocating 16^3 * 2 bytes (8 KiB) for word-initial triphones
INFO: dict2pid.c(131): Allocated 3136 bytes (3 KiB) for word-final triphones
INFO: dict2pid.c(195): Allocated 3136 bytes (3 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=8, 2=10, 3=13
INFO: ngram_model_dmp.c(241): 8 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(289): 10 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314): 13 = LM.trigrams read
INFO: ngram_model_dmp.c(338): 4 = LM.prob2 entries read
INFO: ngram_model_dmp.c(357): 5 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(377): 3 = LM.prob3 entries read
INFO: ngram_model_dmp.c(405): 1 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(461): 8 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 8 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 4 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, 4 single-phone words
INFO: ngram_search_fwdtree.c(324): after: max nonroot chan increased to 138
INFO: ngram_search_fwdtree.c(333): after: 5 root, 10 non-root channels, 3 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: Feb 21 2011, AT: 22:31:47
READY....
错误: ERROR: "ngram_model_arpa.c", line 76: No \data\ mark in LM file 可忽略跳过
警告: Warning: Could not find Mic element 提示找不到麦克。。。
修正执行命令:./pocketsphinx_continuous -adcdev hw:AudioPCI -hmm my_db.cd_cont_1000 -lm my_db.lm.DMP -dict my_db.dic
二、第二次
#./pocketsphinx_continuous -adcdev hw:AudioPCI -hmm my_db.cd_cont_1000 -lm my_db.lm.DMP -dict my_db.dic
INFO: cmd_ln.c(512): Parsing command line:
./pocketsphinx_continuous \
-hmm my_db.cd_cont_1000 \
-lm my_db.lm.DMP \
-dict my_db.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 my_db.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 my_db.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 my_db.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 my_db.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: my_db.cd_cont_1000/mdef
INFO: bin_mdef.c(173): Allocating 304 * 8 bytes (2 KiB) for CD tree
INFO: tmat.c(205): Reading HMM transition probability matrices: my_db.cd_cont_1000/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/means
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/variances
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(356): 30781 variance values floored
INFO: acmod.c(119): Attempting to use PTHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/means
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/variances
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(356): 30781 variance values floored
INFO: ptm_mgau.c(671): Reading mixture weights file 'my_db.cd_cont_1000/mixture_weights'
INFO: ptm_mgau.c(765): Read 105 x 1 x 8 mixture weights
INFO: ptm_mgau.c(831): Maximum top-N: 4
INFO: dict.c(294): Allocating 4112 * 20 bytes (80 KiB) for word entries
INFO: dict.c(306): Reading main dictionary: my_db.dic
INFO: dict.c(206): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(309): 13 words read
INFO: dict.c(314): Reading filler dictionary: my_db.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(396): Building PID tables for dictionary
INFO: dict2pid.c(405): Allocating 16^3 * 2 bytes (8 KiB) for word-initial triphones
INFO: dict2pid.c(131): Allocated 3136 bytes (3 KiB) for word-final triphones
INFO: dict2pid.c(195): Allocated 3136 bytes (3 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=8, 2=10, 3=13
INFO: ngram_model_dmp.c(241): 8 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(289): 10 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314): 13 = LM.trigrams read
INFO: ngram_model_dmp.c(338): 4 = LM.prob2 entries read
INFO: ngram_model_dmp.c(357): 5 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(377): 3 = LM.prob3 entries read
INFO: ngram_model_dmp.c(405): 1 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(461): 8 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 8 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 4 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, 4 single-phone words
INFO: ngram_search_fwdtree.c(324): after: max nonroot chan increased to 138
INFO: ngram_search_fwdtree.c(333): after: 5 root, 10 non-root channels, 3 single-phone words
INFO: ngram_search_fwdflat.c(153): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(261): ./pocketsphinx_continuous COMPILED ON: Feb 21 2011, AT: 22:31:47
READY....
Listening…
segment default….
1、-adcde 设备选择中hw:AudioPCI 、pulseaudio、alsa三者都试过,只有hw:AudioPCI可以成功。
2、向麦克风中说命令,发现出现segment default。
三、第三次使用
(1)重新录下五个.wav音频文件,使每个录音时间超过5s,保存为之前相同的名字。
(2)
./pocketsphinx_continuous -adcdev hw:AudioPCIhmm my_db.cd_cont_1000 -lm my_db.lm.DMP -dict my_db.dic
INFO: cmd_ln.c(512): Parsing command line:
./pocketsphinx_continuous \
-adcdev hw:AudioPCI \
-hmm my_db.cd_cont_1000 \
-lm my_db.lm.DMP \
-dict my_db.dic
Current configuration:
[NAME] [DEFLT] [VALUE]
-adcdev hw:AudioPCI
-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 my_db.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 my_db.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 my_db.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 my_db.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: my_db.cd_cont_1000/mdef
INFO: bin_mdef.c(173): Allocating 166 * 8 bytes (1 KiB) for CD tree
INFO: tmat.c(205): Reading HMM transition probability matrices: my_db.cd_cont_1000/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/means
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/variances
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(356): 16644 variance values floored
INFO: acmod.c(119): Attempting to use PTHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/means
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: my_db.cd_cont_1000/variances
INFO: ms_gauden.c(292): 105 codebook, 1 feature, size
8x39
INFO: ms_gauden.c(356): 16644 variance values floored
INFO: ptm_mgau.c(671): Reading mixture weights file 'my_db.cd_cont_1000/mixture_weights'
INFO: ptm_mgau.c(765): Read 105 x 1 x 8 mixture weights
INFO: ptm_mgau.c(831): Maximum top-N: 4
INFO: dict.c(294): Allocating 4104 * 20 bytes (80 KiB) for word entries
INFO: dict.c(306): Reading main dictionary: my_db.dic
INFO: dict.c(206): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(309): 5 words read
INFO: dict.c(314): Reading filler dictionary: my_db.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(396): Building PID tables for dictionary
INFO: dict2pid.c(405): Allocating 16^3 * 2 bytes (8 KiB) for word-initial triphones
INFO: dict2pid.c(131): Allocated 3136 bytes (3 KiB) for word-final triphones
INFO: dict2pid.c(195): Allocated 3136 bytes (3 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=8, 2=10, 3=13
INFO: ngram_model_dmp.c(241): 8 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(289): 10 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314): 13 = LM.trigrams read
INFO: ngram_model_dmp.c(338): 4 = LM.prob2 entries read
INFO: ngram_model_dmp.c(357): 5 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(377): 3 = LM.prob3 entries read
INFO: ngram_model_dmp.c(405): 1 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(461): 8 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 5 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 4 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, 4 single-phone words
INFO: ngram_search_fwdtree.c(324): after: max nonroot chan increased to 138
INFO: ngram_search_fwdtree.c(333): after: 5 root, 10 non-root channels, 3 single-phone words
INFO: ngram_search_fwdflat.c(153): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(261): ./pocketsphinx_continuous COMPILED ON: Feb 21 2011, AT: 22:31:47
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 < 6.57 -0.33 0.07 -0.15 -0.02 -0.09 0.01 -0.15 -0.04 -0.06 -0.02 -0.06 -0.11 >
INFO: ngram_search_fwdtree.c(1513): 122 words recognized (2/fr)
INFO: ngram_search_fwdtree.c(1515): 534 senones evaluated (8/fr)
INFO: ngram_search_fwdtree.c(1517): 271 channels searched (4/fr), 59 1st, 151 last
INFO: ngram_search_fwdtree.c(1521): 151 words for which last channels evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1524): 5 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): 1 words recognized (0/fr)
INFO: ngram_search_fwdflat.c(914): 402 senones evaluated (6/fr)
INFO: ngram_search_fwdflat.c(916): 136 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(918): 66 words searched (1/fr)
INFO: ngram_search_fwdflat.c(920): 48 word transitions (0/fr)
WARNING: "ngram_search.c", line 1087: </s> not found in last frame, using <s> instead
INFO: ngram_search.c(1137): lattice start node <s>.0 end node <s>.0
INFO: ps_lattice.c(1228): Normalizer P(O) = alpha(<s>:0:2) = -536874752
000000000: (null) (4427764)
READY....
Listening...
Stopped listening, please wait...
INFO: cmn_prior.c(121): cmn_prior_update: from < 6.57 -0.33 0.07 -0.15 -0.02 -0.09 0.01 -0.15 -0.04 -0.06 -0.02 -0.06 -0.11 >
INFO: cmn_prior.c(139): cmn_prior_update: to < 6.59 -0.43 0.10 0.01 0.02 -0.07 -0.01 -0.13 -0.01 -0.09 -0.05 -0.10 -0.08 >
INFO: ngram_search_fwdtree.c(1513): 55 words recognized (1/fr)
INFO: ngram_search_fwdtree.c(1515): 489 senones evaluated (8/fr)
INFO: ngram_search_fwdtree.c(1517): 199 channels searched (3/fr), 33 1st, 97 last
INFO: ngram_search_fwdtree.c(1521): 97 words for which last channels evaluated (1/fr)
INFO: ngram_search_fwdtree.c(1524): 28 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): 22 words recognized (0/fr)
INFO: ngram_search_fwdflat.c(914): 330 senones evaluated (5/fr)
INFO: ngram_search_fwdflat.c(916): 114 channels searched (1/fr)
INFO: ngram_search_fwdflat.c(918): 68 words searched (1/fr)
INFO: ngram_search_fwdflat.c(920): 31 word transitions (0/fr)
WARNING: "ngram_search.c", line 1087: </s> not found in last frame, using <sil> instead
INFO: ngram_search.c(1137): lattice start node <s>.0 end node <sil>.41
INFO: ps_lattice.c(1228): Normalizer P(O) = alpha(<sil>:41:59) = -79841
INFO: ps_lattice.c(1266): Joint P(O,S) = -79841 P(S|O) = 0
000000001: 右转 (-1415156)
READY....
主要参考网地:
1. http://cmusphinx.sourceforge.net/wiki/
2. http://cmusphinx.sourceforge.net/wiki/faq
3. http://ronaldramdhan.wordpress.com/2010/03/11/sphinxtrain/
4. http://sourceforge.net/projects/cmusphinx/forums/forum/5471/topic/3939028
2011年3月2日
转载于:https://my.oschina.net/VenusV/blog/703406
Sphinx武林秘籍(下)相关推荐
- Sphinx武林秘籍(上)
为什么80%的码农都做不了架构师?>>> Sphinx武林秘籍(上) ――使用现有的语言模型与声学模型 一. 使用平台 Windows XP.VMware workst ...
- Sphinx武林秘籍(中)
为什么80%的码农都做不了架构师?>>> Sphinx武林秘籍(中) ――训练自已的中文语言模型与声学模型 一.训练语言模型 (1) 安装语言模型训练工具CMUCLMTK ...
- JAVAWEB增删改查武林秘籍
增删改查武林秘籍 学之受用无穷,可在30分钟内写完增删改查所有后台代码 1.项目搭建 1:创建一个maven 带骨架webapp的项目 2:创建表:book表(你所要增删改查的表) 并且使用idea ...
- 计算机界的“武林秘籍”——经典教材推荐
本文来源于网络,对最经典的教材进行了排行,堪称计算机界的"武林秘籍",秘籍在手,谁与争锋!整理后全文如下: 几年前,台湾著名技术作家侯捷先生曾经写过一篇影响很大的书评文章,叫做&l ...
- 武林秘籍之Spring AOP 切面编程的简单应用
年轻人,我观你骨骼精奇,定是万里无一的练武奇才,老夫这里有一本失传已久的武林秘籍,现赠于你,望你勤加苦练,早日修成正果... AOP(面向切面编程):Aspect Oriented Programmi ...
- Qt武林秘籍学习笔记摘要
1 原文链接 Qt开发经验: 自己总结的这十多年来做Qt开发以来的经验,以及Qt相关武林秘籍电子书,会一直持续更新增加,欢迎各位留言增加内容或者提出建议,谢谢! (gitee.com) 编程语录: 自 ...
- 基金套利的常见招数:高人套利手法像武林秘籍
[题外话] 有人的地方就有江湖. 如今,在巨大的财富效应面前,投资基金已经成为一场"全民运动".虽然基金是强调价值投资的中长期投资品种,买入并长期持有就会有不错的收益,但江湖中人并 ...
- 大佬的QT武林秘籍(整理)
根据大佬的武林秘籍,整理出来一些网的时候自己可以直接查看 大佬主页:https://blog.csdn.net/feiyangqingyun?type=blog 1.QTimer::singleSho ...
- sphinx在windows下的简单安装与使用
1.下载地址 http://sphinxsearch.com/downloads/release/,我这里下的是"Win64 binaries w/MySQL+PgSQL+libstemme ...
最新文章
- POJ 1190 生日蛋糕 【DFS + 极限剪枝】
- Project interpreter not specified(eclipse+pydev) (转)
- vfp语言第 代计算机语言,VFP语言属于第()代计算机语言。A、一B、二C、三D、四...
- 别怀疑,换了位置就该换你的脑袋(转)
- 设计模式之动态代理的代码实现(Java)
- StringBuffer和StringBuilder使用方法比較
- P1368-工艺【最小表示法】
- 你的代码(软件)安全吗?【信息图】
- Oracle全备增量备份脚本,ORACLE-RMAN:备份脚本(全库,增量)
- java Hashtable 和 HashiMap 的区别
- 关于笔记本安装Deepin 或者ubuntu操作系统,无法进入界面。
- java使用d3_D3 快速入门指北
- 小迪渗透Waf绕过(陆)
- python编程自然数表达式_实现四则运算 (python实现)by 周乃君 张宏根
- python人脸识别项目_face++与python实现人脸识别签到(考勤)功能
- 热更新原理及实践注意
- Win10将某个软件/文件添加到开始屏幕(磁贴)
- rr rom Android6,RR ROM 手把手教学刷入和体验
- 2019河南省第十二届ACM大学生程序设计竞赛参赛感
- 还记得啤酒和尿不湿的故事吗?我用Python带你一起玩玩关联规则!