mefistody
|
How do I switch to tidbits acoustic model? I can’t find a way to do it except changing the path directly on the pocketsphinx.c file (which I am sure it’s not the way). Also, when changing it directly it doesn’t recognize any number.
Thanks
|
Halle
|
You should be able to just completely remove the WSJ model from your project (this step is _very_ important) and then drag in the tidgits. Let me know if that isn’t effective. You will of course also have to replace the language model and dictionary with numbers in order to get any recognition.
|
mefistody
|
I’ve tried and didn’t work.
When I compiled I get EXC_BAD_ACCESS error on the line : “if (ps->search==NULL)”
ps_start_utt(ps_decoder_t *ps, char const *uttid)
{
FILE *mfcfh = NULL;
FILE *rawfh = NULL;
int rv;
if (ps->search == NULL) {
E_ERROR("No search module is selected, did you forget to "
"specify a language model or grammar?\n");
return -1;
}
ptmr_reset(&ps->perf);
|
mefistody
|
it’s a long log.
The error shows after listening:
INFO: cmd_ln.c(512): Parsing command line:
\
-lm /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app/6326.languagemodel \
-dict /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app/6326.dic \
-fdict /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app/noisedict \
-hmm /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app \
-maxhmmpf 3000 \
-maxwpf 5
Current configuration:
[NAME] [DEFLT] [VALUE]
-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 /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app/6326.dic
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app/noisedict
-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 /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app
-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 /var/mobile/Applications/35F25888-DF7F-46B7-894D-35A5B9138D53/OE_Test01.app/6326.languagemodel
-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 3000
-maxnewoov 20 20
-maxwpf -1 5
-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: 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
ERROR: “acmod.c”, line 84: Must specify -mdef or -hmm
2011-11-23 11:49:29.156 OE_Test01[454:230b] OPENEARSLOGGING: Starting openAudioDevice on the device.
2011-11-23 11:49:29.170 OE_Test01[454:230b] OPENEARSLOGGING: Audio unit wrapper successfully created.
2011-11-23 11:49:29.180 OE_Test01[454:707] Pocketsphinx is starting up.
2011-11-23 11:49:29.217 OE_Test01[454:230b] OPENEARSLOGGING: Set audio route to SpeakerAndMicrophone
2011-11-23 11:49:29.221 OE_Test01[454:230b] OPENEARSLOGGING: Setting the variables for the device and starting it.
2011-11-23 11:49:29.225 OE_Test01[454:230b] OPENEARSLOGGING: Looping through ringbuffer sections and pre-allocating them.
2011-11-23 11:49:29.858 OE_Test01[454:230b] OPENEARSLOGGING: Started audio output unit.
2011-11-23 11:49:29.862 OE_Test01[454:230b] OPENEARSLOGGING: Calibration has started
2011-11-23 11:49:29.864 OE_Test01[454:707] Pocketsphinx calibration has started.
2011-11-23 11:49:34.118 OE_Test01[454:230b] OPENEARSLOGGING: Calibration has completed
2011-11-23 11:49:34.120 OE_Test01[454:707] Pocketsphinx calibration is complete.
2011-11-23 11:49:34.125 OE_Test01[454:230b] OPENEARSLOGGING: Project has these words in its dictionary:
BLACK
BLUE
CIRCLE
EIGHT
FIVE
FOUR
JUMP
NINE
ONE
ONE(2)
ORANGE
ORANGE(2)
RED
SEVEN
SIX
SQUARE
STAR
TEN
THREE
TRIANGLE
TWO
YELLOW
2011-11-23 11:49:34.130 OE_Test01[454:230b] OPENEARSLOGGING: Listening.
2011-11-23 11:49:34.135 OE_Test01[454:707] Pocketsphinx is now listening.
[Switching to process 8963 thread 0x2303]
[Switching to process 8963 thread 0x2303]
|
Halle
|
It says that you didn’t successfully import the acoustic model. It isn’t finding it in the app bundle.
|
mefistody
|
I am confused with language model and acoustic model.
What’s the acoustic model? Where do I find it?
|
Halle
|
Please just review the OpenEars documentation until you are clear on that — it’s all in there. It’s premature to attempt changing to a different acoustic model if you aren’t sure yet what it is.
|
AllHours
3 Numbers
AllEars
OpenEars
Our Flying Friends