I try to install Pocketsphinx in French on a Buildroot embedded device. So I dowloaded the default french language model: https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/French/
I tried several times to make pocketsphinx works using command line on the embedded device, but it failed each time. I learned that it could be caused by the huge size of my dictionary (~ 100 000 words, called fr.dict), so I created a much smaller dictionary of 100 words (called fr-test.dict). But it doesn't seem to have changed anything.
I use the pocketsphinx_continuous command line. I defined a hmm, a dictionary and a language model which are pulled out from this folder :
Three differents hmm:
cmusphinx-fr-5.2
cmusphinx-fr-ptm-5.2
cmusphinx-fr-ptm-8khz-5.2
Two dictionaries:
fr.dict
fr-test.dict
And three language models
fr.lm.dmp
fr-small.lm.bin
fr-phone.lm.dmp
The first two parameters doesn't seem to change anything. However, the thrid one does change the error messages I receive.
With the first lm (fr.lm.dmp) the complete log are:
# pocketsphinx_continuous -adcdev plug:pcm.mic -inmic yes -hmm /mnt/usb/sphinx-f
rench/cmusphinx-fr-5.2 -lm /mnt/usb/sphinx-french/fr.lm.dmp -dict /mnt/usb/sphin
x-french/
INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from /mnt/usb/sphinx-french/cmusphinx-fr-5.2/feat.params
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-allphone
-allphone_ci no no
-alpha 0.97 9.700000e-01
-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
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict /mnt/usb/sphinx-french/
-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 /mnt/usb/sphinx-french/cmusphinx-fr-5.2
-input_endian little little
-jsgf
-keyphrase
-kws
-kws_delay 10 10
-kws_plp 1e-1 1.000000e-01
-kws_threshold 1 1.000000e+00
-latsize 5000 5000
-lda
-ldadim 0 0
-lifter 0 22
-lm /mnt/usb/sphinx-french/fr.lm.dmp
-lmctl
-lmname
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.300000e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf 30000 30000
-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 25
-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-10 1.000000e-10
-pl_pip 1.0 1.000000e+00
-pl_weight 3.0 3.000000e+00
-pl_window 5 5
-rawlogdir
-remove_dc no no
-remove_noise yes yes
-remove_silence yes yes
-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
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 6.800000e+03
-uw 1.0 1.000000e+00
-vad_postspeech 50 50
-vad_prespeech 20 20
-vad_startspeech 10 10
-vad_threshold 2.0 2.000000e+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: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(143): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(152): Reading linear feature transformation from /mnt/usb/sphinx-french/cmusphinx-fr-5.2/feature_transform
INFO: mdef.c(518): Reading model definition: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/mdef
INFO: bin_mdef.c(181): Allocating 101051 * 8 bytes (789 KiB) for CD tree
INFO: tmat.c(149): Reading HMM transition probability matrices: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/transition_matrices
INFO: acmod.c(113): Attempting to use PTM computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/means
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/variances
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(304): 0 variance values floored
INFO: ptm_mgau.c(804): Number of codebooks exceeds 256: 2108
INFO: acmod.c(115): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/means
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/variances
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(304): 0 variance values floored
INFO: acmod.c(117): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/means
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/variances
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(304): 0 variance values floored
INFO: ms_senone.c(149): Reading senone mixture weights: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/mixture_weights
INFO: ms_senone.c(200): Truncating senone logs3(pdf) values by 10 bits
INFO: ms_senone.c(207): Not transposing mixture weights in memory
INFO: ms_senone.c(268): Read mixture weights for 2108 senones: 1 features x 8 codewords
INFO: ms_senone.c(320): Mapping senones to individual codebooks
INFO: ms_mgau.c(144): The value of topn: 4
INFO: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0
INFO: dict.c(320): Allocating 4099 * 20 bytes (80 KiB) for word entries
INFO: dict.c(333): Reading main dictionary: /mnt/usb/sphinx-french/
INFO: dict.c(213): Dictionary size 0, allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(336): 0 words read
INFO: dict.c(358): Reading filler dictionary: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/noisedict
INFO: dict.c(213): Dictionary size 3, allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(361): 3 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 36^3 * 2 bytes (91 KiB) for word-initial triphones
INFO: dict2pid.c(132): Allocated 15696 bytes (15 KiB) for word-final triphones
INFO: dict2pid.c(196): Allocated 15696 bytes (15 KiB) for single-phone word triphones
INFO: ngram_model_trie.c(347): Trying to read LM in trie binary format
INFO: ngram_model_trie.c(358): Header doesn't match
INFO: ngram_model_trie.c(176): Trying to read LM in arpa format
INFO: ngram_model_trie.c(69): No \data\ mark in LM file
INFO: ngram_model_trie.c(438): Trying to read LM in DMP format
INFO: ngram_model_trie.c(520): ngrams 1=62304, 2=18541132, 3=23627127
calloc(23627127,16) failed from ngrams_raw.c(278)
With the two others, I receive these logs:
# pocketsphinx_continuous -adcdev plug:pcm.mic -inmic yes -hmm /mnt/usb/sphinx-f
rench/cmusphinx-fr-5.2 -lm /mnt/usb/sphinx-french/fr-phone.lm.dmp -dict /mnt/usb
/sphinx-french/fr.dict
INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from /mnt/usb/sphinx-french/cmusphinx-fr-5.2/feat.params
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-allphone
-allphone_ci no no
-alpha 0.97 9.700000e-01
-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
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict /mnt/usb/sphinx-french/fr.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 /mnt/usb/sphinx-french/cmusphinx-fr-5.2
-input_endian little little
-jsgf
-keyphrase
-kws
-kws_delay 10 10
-kws_plp 1e-1 1.000000e-01
-kws_threshold 1 1.000000e+00
-latsize 5000 5000
-lda
-ldadim 0 0
-lifter 0 22
-lm /mnt/usb/sphinx-french/fr-phone.lm.dmp
-lmctl
-lmname
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.300000e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf 30000 30000
-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 25
-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-10 1.000000e-10
-pl_pip 1.0 1.000000e+00
-pl_weight 3.0 3.000000e+00
-pl_window 5 5
-rawlogdir
-remove_dc no no
-remove_noise yes yes
-remove_silence yes yes
-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
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 6.800000e+03
-uw 1.0 1.000000e+00
-vad_postspeech 50 50
-vad_prespeech 20 20
-vad_startspeech 10 10
-vad_threshold 2.0 2.000000e+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: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(143): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(152): Reading linear feature transformation from /mnt/usb/sphinx-french/cmusphinx-fr-5.2/feature_transform
INFO: mdef.c(518): Reading model definition: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/mdef
INFO: bin_mdef.c(181): Allocating 101051 * 8 bytes (789 KiB) for CD tree
INFO: tmat.c(149): Reading HMM transition probability matrices: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/transition_matrices
INFO: acmod.c(113): Attempting to use PTM computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/means
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/variances
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(304): 0 variance values floored
INFO: ptm_mgau.c(804): Number of codebooks exceeds 256: 2108
INFO: acmod.c(115): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/means
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/variances
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(304): 0 variance values floored
INFO: acmod.c(117): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/means
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/variances
INFO: ms_gauden.c(242): 2108 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x32
INFO: ms_gauden.c(304): 0 variance values floored
INFO: ms_senone.c(149): Reading senone mixture weights: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/mixture_weights
INFO: ms_senone.c(200): Truncating senone logs3(pdf) values by 10 bits
INFO: ms_senone.c(207): Not transposing mixture weights in memory
INFO: ms_senone.c(268): Read mixture weights for 2108 senones: 1 features x 8 codewords
INFO: ms_senone.c(320): Mapping senones to individual codebooks
INFO: ms_mgau.c(144): The value of topn: 4
INFO: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0
INFO: dict.c(320): Allocating 109102 * 20 bytes (2130 KiB) for word entries
INFO: dict.c(333): Reading main dictionary: /mnt/usb/sphinx-french/fr.dict
INFO: dict.c(213): Dictionary size 105003, allocated 1018 KiB for strings, 1375 KiB for phones
INFO: dict.c(336): 105003 words read
INFO: dict.c(358): Reading filler dictionary: /mnt/usb/sphinx-french/cmusphinx-fr-5.2/noisedict
INFO: dict.c(213): Dictionary size 105006, allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(361): 3 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 36^3 * 2 bytes (91 KiB) for word-initial triphones
INFO: dict2pid.c(132): Allocated 15696 bytes (15 KiB) for word-final triphones
INFO: dict2pid.c(196): Allocated 15696 bytes (15 KiB) for single-phone word triphones
INFO: ngram_model_trie.c(347): Trying to read LM in trie binary format
INFO: ngram_model_trie.c(358): Header doesn't match
INFO: ngram_model_trie.c(176): Trying to read LM in arpa format
INFO: ngram_model_trie.c(69): No \data\ mark in LM file
INFO: ngram_model_trie.c(438): Trying to read LM in DMP format
INFO: ngram_model_trie.c(520): ngrams 1=38, 2=1240, 3=23231
INFO: lm_trie.c(473): Training quantizer
INFO: lm_trie.c(481): Building LM trie
INFO: ngram_search_fwdtree.c(74): Initializing search tree
INFO: ngram_search_fwdtree.c(101): 742 unique initial diphones
INFO: ngram_search_fwdtree.c(186): Creating search channels
INFO: ngram_search_fwdtree.c(323): Max nonroot chan increased to 136
INFO: ngram_search_fwdtree.c(333): Created 12 root, 8 non-root channels, 14 single-phone words
INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(307): pocketsphinx_continuous COMPILED ON: Apr 18 2019, AT: 18:26:09
INFO: continuous.c(252): Ready....
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)
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)
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)
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)
A new "Input overrun" log appear every second. And remember these results does not change with another hmm or a smaller dictionary.
Any idea what is happening and how I can solve the problem ?
