Closed Teslafly closed 10 years ago
Are You using Debian? There seem to be prebuilt packages in experimental.
You could also try to run Jasper without m2m-aligner. I don't know if we need it at all (see issue #191)
Well, I compiled everything else and set up jasper. When I try to run it without m2m aligner I get this:
root@beaglebone:~/jasper/jasper# /root/jasper/jasper/jasper.py
===========================================================
JASPER The Talking Computer
Copyright 2013 Shubhro Saha & Charlie Marsh
===========================================================
ERROR:__main__:Language model or associated files missing.
Traceback (most recent call last):
File "/root/jasper/jasper/jasper.py", line 89, in <module>
app = Jasper()
File "/root/jasper/jasper/jasper.py", line 63, in __init__
vocabcompiler.compile(sentences, dictionary, languagemodel)
File "/root/jasper/jasper/client/vocabcompiler.py", line 43, in compile
pronounced = g2p.translateWords(words)
File "/root/jasper/jasper/client/g2p.py", line 45, in translateWords
output = translateFile(temp_filename)
File "/root/jasper/jasper/client/g2p.py", line 53, in translateFile
['phonetisaurus-g2p', '--model=%s' % FST_MODEL, '--input=%s' % input_filename, '--words', '--isfile'])
File "/usr/lib/python2.7/subprocess.py", line 537, in check_output
process = Popen(stdout=PIPE, *popenargs, **kwargs)
File "/usr/lib/python2.7/subprocess.py", line 679, in __init__
errread, errwrite)
File "/usr/lib/python2.7/subprocess.py", line 1259, in _execute_child
raise child_exception
OSError: [Errno 2] No such file or directory
I do believe that m2m aligner is a prerequisite of Phonetisaurus, so while I'm not quite sure, that may be what's going on here. - unless it's obviously different. My python knowledge is probably a lot sketchier than yours so I can't say if that's actually the error. In the mean time, I'm going to try and install that precompiled m2m package and see how it works out.
Nope, I managed to get the experimental m2m-aligner installed and I got the exact same error message. Could it have something to do with file paths? I put jasper and all it's dependencies in it's own folder for now as the file paths are all retaliative, right?
I guess that the fst model could not be found.
Add this to your profile.yml
:
pocketsphinx:
fst_model: /path/to/g014b2b.fst
By default, Jasper will expect the FST model in $JASPER_HOME/phonetisaurus/g014b2b.fst
, where $JASPER_HOME
is the parent dir of the jasper Installation (the directory above the directory that contains jasper.py
).
Well, I tried your suggestions to no avail. I made sure my go14b2b.fst was in $JASPER_HOME/phonetisaurus/g014b2b.fst
as can be seen here:
root@beaglebone:~/jasper/phonetisaurus# pwd
/root/jasper/phonetisaurus
root@beaglebone:~/jasper/phonetisaurus# ls
README.txt compile-fst.sh g014b2b.arpa g014b2b.corpus g014b2b.fst g014b2b.fst.txt g014b2b.hyp g014b2b.isyms g014b2b.osyms g014b2b.ref g014b2b.ssyms g014b2b.train g014b2b.words
root@beaglebone:~/jasper/jasper# pwd
/root/jasper/jasper
root@beaglebone:~/jasper/jasper# ls
CONTRIBUTING.md README.md boot client jasper.py static
And just for good measure, I added the path to the profile.yml file, which can be seen below (With sensitive information removed of course)
pocketsphinx:
fst_model: /root/jasper/phonetisaurus/g014b2b.fst
carrier: ----------
first_name: ----------
gmail_address:----------
gmail_password: -----------
last_name: ----------
location: ----------
phone_number: ----------
prefers_email: true
stt_engine: sphinx
timezone: America/Boise
Yet, I am still getting the exact same error on trying to start jasper. I then tried recompiling g014b2b:
root@beaglebone:~/jasper/phonetisaurus# ./compile-fst.sh
fstcompile --ssymbols=g014b2b.ssyms --isymbols=g014b2b.isyms --keep_isymbols --osymbols=g014b2b.osyms --keep_osymbols g014b2b.fst.txt > g014b2b.fst
root@beaglebone:~/jasper/phonetisaurus#
And after got the same results.
Does any of this look wrong to you? And if everything looks ok, what would you suggest for debugging? I did find some potentially useful info in #168 and may try some of the suggestions in a little while. I am a bit confused about this part though set the JASPER_HOME variable in my ./bashrc script
. (You are dealing with someone that has found their way around the linux command line using google) Also, I think I see where m2m may be needed. In the phonetisaurus(g014b2b) folder there is a README.txt file with the following info:
Standard g014b2b training/testing run
Commands run from the 'script' subdirectory of a standard phonetisaurus distribution.
Setup
$ mkdir g014b2b
Aligner command (default)
$ ../m2m-aligner.py -s1 -s2 -wa g014b2b/g014b2b.corpus -a ../partitions/g014b2b.train.fix.bsf
Training command (mitlm)
$ ./train-model.py --smoothing FixModKN --dict ../partitions/g014b2b.train.fix.bsf --prefix g014b2b/g014b2b --noalign --palign --order 15
Evaluation command
$ ./evaluate.py --modelfile g014b2b/g014b2b.fst --testfile ../partitions/g014b2b.test.fix.bsf --prefix g014b2b/g014b2b
Words: 12000 Hyps: 12000 Refs: 12000
######################################################################
EVALUATION RESULTS
----------------------------------------------------------------------
(T)otal tokens in reference: 75777
(M)atches: 71705 (S)ubstitutions: 3629 (I)nsertions: 374 (D)eletions: 443
% Correct (M/T) -- %94.63
% Token ER ((S+I+D)/T) -- %5.87
% Accuracy 1.0-ER -- %94.13
--------------------------------------------------------
(S)equences: 12000 (C)orrect sequences: 9060 (E)rror sequences: 2940
% Sequence ER (E/S) -- %24.50
% Sequence Acc (1.0-E/S) -- %75.50
######################################################################
Since a recent commit $JASPER_HOME
is not used anymore.
So forgive me if I'm a bit ignorant here (I am, sorry), but what does that mean for me? I forced a git pull and am still getting the same error. I may just scrap the install and try everything from scratch as I may have inadvertently screwed anything up along the way.
EDIT: I deteted and redownloaded both the jasper core files and g014b2b, and now the error has gone away, replaced with some sort of jasper "boot loop", of which a sample can be found below. (full printout can be found here)
root@beaglebone:/home/pi/jasper# ./jasper.py
===========================================================
JASPER The Talking Computer
Copyright 2013 Shubhro Saha & Charlie Marsh
===========================================================
Symbol: ' ' not found in input symbols table.
Mapping to null...
text2idngram
Vocab : /home/pi/jasper/client/sentences.txt
Output idngram : temp.idngram
N-gram buffer size : 100
Hash table size : 2000000
Temp directory : cmuclmtk-TqXx7K
Max open files : 20
FOF size : 10
n : 3
Initialising hash table...
Reading vocabulary...
Allocating memory for the n-gram buffer...
Reading text into the n-gram buffer...
20,000 n-grams processed for each ".", 1,000,000 for each line.
Sorting n-grams...
Writing sorted n-grams to temporary file cmuclmtk-TqXx7K/1
Merging 1 temporary files...
2-grams occurring: N times > N times Sug. -spec_num value
0 24 34
1 24 0 10
2 0 0 10
3 0 0 10
4 0 0 10
5 0 0 10
6 0 0 10
7 0 0 10
8 0 0 10
9 0 0 10
10 0 0 10
and towards the end
===================
JASPER:
===================
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm_dmix.c:957:(snd_pcm_dmix_open) The dmix plugin supports only playback stream
Cannot connect to server socket err = No such file or directory
Cannot connect to server request channel
jack server is not running or cannot be started
Also, is all the info on this page still relevant? it's what I based my install on and if the instructions there wouldn't even work for a raspi build (I have no way of testing this) then no wonder it isn't working on the BBB. I'm sorry if this is rapidly turning into a tech support thread for something you don't support, but I am quickly getting out of my skill range here (which mostly includes the Linux terminal and googling tech problems intelligently)
Please post the absolute paths of jasper.py
and the fst file.
And please check if the phonetisaurus-g2p
command exists.
I Probably shouldn't have posted my above comment yet, as I ended up making a big edit after you commented.(edit repeated below)
EDIT: I deteted and redownloaded both the jasper core files and g014b2b, and now the error has gone away, replaced with some sort of jasper "boot loop", of which a sample can be found below. (full printout can be found here)
root@beaglebone:/home/pi/jasper# ./jasper.py
===========================================================
JASPER The Talking Computer
Copyright 2013 Shubhro Saha & Charlie Marsh
===========================================================
Symbol: ' ' not found in input symbols table.
Mapping to null...
text2idngram
Vocab : /home/pi/jasper/client/sentences.txt
Output idngram : temp.idngram
N-gram buffer size : 100
Hash table size : 2000000
Temp directory : cmuclmtk-TqXx7K
Max open files : 20
FOF size : 10
n : 3
Initialising hash table...
Reading vocabulary...
Allocating memory for the n-gram buffer...
Reading text into the n-gram buffer...
20,000 n-grams processed for each ".", 1,000,000 for each line.
Sorting n-grams...
Writing sorted n-grams to temporary file cmuclmtk-TqXx7K/1
Merging 1 temporary files...
2-grams occurring: N times > N times Sug. -spec_num value
0 24 34
1 24 0 10
2 0 0 10
3 0 0 10
4 0 0 10
5 0 0 10
6 0 0 10
7 0 0 10
8 0 0 10
9 0 0 10
10 0 0 10
and towards the end
===================
JASPER:
===================
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm_dmix.c:957:(snd_pcm_dmix_open) The dmix plugin supports only playback stream
Cannot connect to server socket err = No such file or directory
Cannot connect to server request channel
jack server is not running or cannot be started
Oh, and I moved everything to /home/pi like it would be in a regular pi. I am still running under the root user though. (If you still want me to post the absolute paths now I will, but I'm not sure that is needed anymore.)
I'll post another comment once 'phonetisaurus-g2p' returns something. right now it appears to be hanging and has no output or fail. (it's been running for 2 min or so)
Left it for a couple hours. It seems to have just hung (the BBB was otherwise responsive though, so it wasn't crunching numbers or crashing the system either)
root@beaglebone:/home/pi# phonetisaurus-g2p
^C
root@beaglebone:/home/pi#
it obviously exists, but I don't think it's working correctly. or an I seeing if it exists wrong?
I'm just going to go ahead and rebuild with a fresh image. on the emmc this time as well.
ok, I rebuild jasper on the on-board emmc with a fresh debian image. using some variations on the instructions I initially posted, I got to the point where jasper would start, but wouldn't finish, throwing itself onto a loop with the last line being jack server is not running or cannot be started'. So, here comes the debug stuff. When I try to run
pocketsphinx_continuous`
I get this output
root@beaglebone:~# pocketsphinx_continuous
INFO: cmd_ln.c(691): Parsing command line:
pocketsphinx_continuous
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
-aw 1 1
-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
-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
-infile
-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
-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
-min_endfr 0 0
-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
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec
-time no no
-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:
\
-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+00
-alpha 0.97 9.700000e-01
-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+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-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+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(246): Parsed model-specific feature parameters from /usr/local/sha re/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model /hmm/en_US/hub4wsj_sc_8k/mdef
INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef fi le
INFO: bin_mdef.c(336): Reading binary model definition: /usr/local/share/pockets phinx/model/hmm/en_US/hub4wsj_sc_8k/mdef
INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-s en, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: /usr/local/share /pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices
INFO: acmod.c(121): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/poc ketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/poc ketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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 /usr/local/share/pocke tsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump
INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION
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 137543 * 20 bytes (2686 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: /usr/local/share/pocketsphinx/model/ lm/en_US/cmu07a.dic
INFO: dict.c(211): Allocated 1010 KiB for strings, 1664 KiB for phones
INFO: dict.c(335): 133436 words read
INFO: dict.c(341): Reading filler dictionary: /usr/local/share/pocketsphinx/mode l/hmm/en_US/hub4wsj_sc_8k/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 trip hones
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 trip hones
INFO: ngram_model_arpa.c(77): No \data\ mark in LM file
INFO: ngram_model_dmp.c(142): Will use memory-mapped I/O for LM file
INFO: ngram_model_dmp.c(196): ngrams 1=5001, 2=436879, 3=418286
INFO: ngram_model_dmp.c(242): 5001 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(288): 436879 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314): 418286 = LM.trigrams read
INFO: ngram_model_dmp.c(339): 37293 = LM.prob2 entries read
INFO: ngram_model_dmp.c(359): 14370 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(379): 36094 = LM.prob3 entries read
INFO: ngram_model_dmp.c(407): 854 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(463): 5001 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 788 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 60 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, 60 singl e-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 13428
INFO: ngram_search_fwdtree.c(338): after: 457 root, 13300 non-root channels, 26 single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(371): pocketsphinx_continuous COMPILED ON: Sep 24 2014, AT: 0 4:38:50
Error opening audio device (null) for capture: Connection refused
FATAL_ERROR: "continuous.c", line 246: Failed to open audio device
So pocketsphinx is working, it just can't connect to any microphones. My one and only soundcard is card #0, just like in the rasberry pi.
root@beaglebone:~# aplay -l
**** List of PLAYBACK Hardware Devices ****
card 0: Set [C-Media USB Headphone Set], device 0: USB Audio [USB Audio]
Subdevices: 1/1
Subdevice #0: subdevice #0
both the audio test commands in the jasper install instructions work as well
root@beaglebone:~# arecord temp.wav
Recording WAVE 'temp.wav' : Unsigned 8 bit, Rate 8000 Hz, Mono
^CAborted by signal Interrupt...
root@beaglebone:~# aplay temp.wav
Playing WAVE 'temp.wav' : Unsigned 8 bit, Rate 8000 Hz, Mono
So I'm not exactly sure what the problem with connecting to audio devices is. Is there a way to force pocketsphinx to use a specific audio device?
Next thing, the command phonetisaurus-g2p
exists, bit hangs when run on it's own. it does return a hefty help menu though;
root@beaglebone:~# phonetisaurus-g2p --help
phonetisaurus-g2p decoder.
Usage:
Flags from: flags.cc
--help: type = bool, default = false
show usage information
--helpshort: type = bool, default = false
show brief usage information
--tmpdir: type = string, default = "/tmp/"
temporary directory
--v: type = int32, default = 0
verbose level
Flags from: fst.cc
--fst_align: type = bool, default = false
Write FST data aligned where appropriate
--fst_default_cache_gc: type = bool, default = true
Enable garbage collection of cache
--fst_default_cache_gc_limit: type = int64, default = 1048576
Cache byte size that triggers garbage collection
--fst_read_mode: type = string, default = "read"
Default file reading mode for mappable files
--fst_verify_properties: type = bool, default = false
Verify fst properties queried by TestProperties
--fst_weight_parentheses: type = string, default = ""
Characters enclosing the first weight of a printed composite weight (e.g. pair weight, tuple weight and derived classes) to ensure proper I/O of nested composite weights; must have size 0 (none) or 2 (open and close parenthesis)
--fst_weight_separator: type = string, default = ","
Character separator between printed composite weights; must be a single character
--save_relabel_ipairs: type = string, default = ""
Save input relabel pairs to file
--save_relabel_opairs: type = string, default = ""
Save output relabel pairs to file
Flags from: phonetisaurus-g2p.cpp
--alpha: type = double, default = 0.6
The alpha LM scale factor for the LMBR decoder.
--beam: type = int32, default = 500
N-best search beam.
--input: type = string, default = ""
A word or test file.
--isfile: type = bool, default = false
'--input' is a file.
--mbr: type = bool, default = false
Use the Lattice Minimum Bayes-Risk decoder
--model: type = string, default = ""
The input WFST G2P model.
--nbest: type = int32, default = 1
Print out the N-best pronunciations.
--order: type = int32, default = 6
The N-gram order for the MBR decoder.
--prec: type = double, default = 0.85
The N-gram precision factor for the LMBR decoder.
--ratio: type = double, default = 0.72
The N-gram ratio factor for the LMBR decoder.
--sep: type = string, default = ""
Separator token for input words.
--words: type = bool, default = false
Output words with hypotheses.
Flags from: symbol-table.cc
--fst_compat_symbols: type = bool, default = true
Require symbol tables to match when appropriate
--fst_field_separator: type = string, default = " "
Set of characters used as a separator between printed fields
Flags from: util.cc
--fst_error_fatal: type = bool, default = true
FST errors are fatal; o.w. return objects flagged as bad: e.g., FSTs - kError prop. true, FST weights - not a Member()
finally, the jasper error, it's the same as I ended up with before, but i'll paste the while thing here so it can easily be looked through. hopefully it's just a small thing holding this up, not an exceptionally finicky incompatibility.
root@beaglebone:~/jasper# python jasper.py
===========================================================
JASPER The Talking Computer
Copyright 2013 Shubhro Saha & Charlie Marsh
===========================================================
Symbol: ' ' not found in input symbols table.
Mapping to null...
text2idngram
Vocab : /root/jasper/client/sentences.txt
Output idngram : temp.idngram
N-gram buffer size : 100
Hash table size : 2000000
Temp directory : cmuclmtk-uARb3e
Max open files : 20
FOF size : 10
n : 3
Initialising hash table...
Reading vocabulary...
Allocating memory for the n-gram buffer...
Reading text into the n-gram buffer...
20,000 n-grams processed for each ".", 1,000,000 for each line.
Sorting n-grams...
Writing sorted n-grams to temporary file cmuclmtk-uARb3e/1
Merging 1 temporary files...
2-grams occurring: N times > N times Sug. -spec_num value
0 24 34
1 24 0 10
2 0 0 10
3 0 0 10
4 0 0 10
5 0 0 10
6 0 0 10
7 0 0 10
8 0 0 10
9 0 0 10
10 0 0 10
3-grams occurring: N times > N times Sug. -spec_num value
0 24 34
1 24 0 10
2 0 0 10
3 0 0 10
4 0 0 10
5 0 0 10
6 0 0 10
7 0 0 10
8 0 0 10
9 0 0 10
10 0 0 10
text2idngram : Done.
n : 3
Input file : temp.idngram (binary format)
Output files :
ARPA format : /root/jasper/client/languagemodel.lm
Vocabulary file : /root/jasper/client/sentences.txt
Cutoffs :
2-gram : 0 3-gram : 0
Vocabulary type : Open - type 1
Minimum unigram count : 0
Zeroton fraction : 1
Counts will be stored in two bytes.
Count table size : 65535
Discounting method : Good-Turing
Discounting ranges :
1-gram : 1 2-gram : 7 3-gram : 7
Memory allocation for tree structure :
Allocate 100 MB of memory, shared equally between all n-gram tables.
Back-off weight storage :
Back-off weights will be stored in four bytes.
Reading vocabulary.
read_wlist_into_siht: a list of 25 words was read from "/root/jasper/client/sentences.txt".
read_wlist_into_array: a list of 25 words was read from "/root/jasper/client/sentences.txt".
WARNING: <s> appears as a vocabulary item, but is not labelled as a
context cue.
Allocated space for 3571428 2-grams.
Allocated space for 8333333 3-grams.
table_size 26
Allocated 57142848 bytes to table for 2-grams.
Allocated (2+33333332) bytes to table for 3-grams.
Processing id n-gram file.
20,000 n-grams processed for each ".", 1,000,000 for each line.
Calculating discounted counts.
Warning : 1-gram : Discounting range is 1; setting P(zeroton)=P(singleton).
Discounted value : 0.88
Warning : 2-gram : GT statistics are out of range; lowering cutoff to 6.
Warning : 2-gram : GT statistics are out of range; lowering cutoff to 5.
Warning : 2-gram : GT statistics are out of range; lowering cutoff to 4.
Warning : 2-gram : GT statistics are out of range; lowering cutoff to 3.
Warning : 2-gram : GT statistics are out of range; lowering cutoff to 2.
Warning : 2-gram : GT statistics are out of range; lowering cutoff to 1.
Warning : 2-gram : Discounting range of 1 is equivalent to excluding
singletons.
Warning : 2-gram : GT statistics are out of range; lowering cutoff to 0.
Warning : 2-gram : Discounting is disabled.
Warning : 3-gram : GT statistics are out of range; lowering cutoff to 6.
Warning : 3-gram : GT statistics are out of range; lowering cutoff to 5.
Warning : 3-gram : GT statistics are out of range; lowering cutoff to 4.
Warning : 3-gram : GT statistics are out of range; lowering cutoff to 3.
Warning : 3-gram : GT statistics are out of range; lowering cutoff to 2.
Warning : 3-gram : GT statistics are out of range; lowering cutoff to 1.
Warning : 3-gram : Discounting range of 1 is equivalent to excluding
singletons.
Warning : 3-gram : GT statistics are out of range; lowering cutoff to 0.
Warning : 3-gram : Discounting is disabled.
Unigrams's discount mass is 0.11 (n1/N = 0.916667)
3 zerotons, P(zeroton) = 0.0366667 P(singleton) = 0.0366667
P(zeroton) was reduced to 0.0366666665 (1.000 of P(singleton))
prob[UNK] = 0.0366667
Incrementing contexts...
Calculating back-off weights...
Writing out language model...
ARPA-style 3-gram will be written to /root/jasper/client/languagemodel.lm
idngram2lm : Done.
/usr/bin/espeak
INFO: cmd_ln.c(691): Parsing command line:
\
-hmm /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k \
-lm languagemodel_persona.lm \
-dict dictionary_persona.dic
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-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
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict dictionary_persona.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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k
-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 languagemodel_persona.lm
-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
-min_endfr 0 0
-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
-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:
\
-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+00
-alpha 0.97 9.700000e-01
-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+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-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+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(246): Parsed model-specific feature parameters from /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices
INFO: acmod.c(121): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump
INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION
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 4129 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: dictionary_persona.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 22 words read
INFO: dict.c(341): Reading filler dictionary: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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=20, 2=36, 3=18
INFO: ngram_model_arpa.c(135): Reading unigrams
INFO: ngram_model_arpa.c(516): 20 = #unigrams created
INFO: ngram_model_arpa.c(195): Reading bigrams
INFO: ngram_model_arpa.c(533): 36 = #bigrams created
INFO: ngram_model_arpa.c(534): 3 = #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): 18 = #trigrams created
INFO: ngram_model_arpa.c(556): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 18 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 147
INFO: ngram_search_fwdtree.c(338): after: 18 root, 19 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: cmd_ln.c(691): Parsing command line:
\
-hmm /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k \
-lm languagemodel.lm \
-dict dictionary.dic
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-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
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict dictionary.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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k
-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 languagemodel.lm
-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
-min_endfr 0 0
-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
-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:
\
-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+00
-alpha 0.97 9.700000e-01
-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+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-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+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(246): Parsed model-specific feature parameters from /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices
INFO: acmod.c(121): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump
INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION
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 4130 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: dictionary.dic
ERROR: "dict.c", line 193: Line 20: Phone 'KNOCK' is mising in the acoustic model; word 'KNOCK' ignored
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 22 words read
INFO: dict.c(341): Reading filler dictionary: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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=26, 2=24, 3=24
INFO: ngram_model_arpa.c(135): Reading unigrams
INFO: ngram_model_arpa.c(516): 26 = #unigrams created
INFO: ngram_model_arpa.c(195): Reading bigrams
INFO: ngram_model_arpa.c(533): 24 = #bigrams created
INFO: ngram_model_arpa.c(534): 3 = #prob2 entries
INFO: ngram_model_arpa.c(542): 4 = #bo_wt2 entries
INFO: ngram_model_arpa.c(292): Reading trigrams
INFO: ngram_model_arpa.c(555): 24 = #trigrams created
INFO: ngram_model_arpa.c(556): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 21 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 184
INFO: ngram_search_fwdtree.c(338): after: 21 root, 56 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: cmd_ln.c(691): Parsing command line:
\
-hmm /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k \
-lm languagemodel_persona.lm \
-dict dictionary_persona.dic
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-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
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict dictionary_persona.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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k
-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 languagemodel_persona.lm
-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
-min_endfr 0 0
-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
-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:
\
-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+00
-alpha 0.97 9.700000e-01
-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+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-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+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(246): Parsed model-specific feature parameters from /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices
INFO: acmod.c(121): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump
INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION
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 4129 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: dictionary_persona.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 22 words read
INFO: dict.c(341): Reading filler dictionary: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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=20, 2=36, 3=18
INFO: ngram_model_arpa.c(135): Reading unigrams
INFO: ngram_model_arpa.c(516): 20 = #unigrams created
INFO: ngram_model_arpa.c(195): Reading bigrams
INFO: ngram_model_arpa.c(533): 36 = #bigrams created
INFO: ngram_model_arpa.c(534): 3 = #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): 18 = #trigrams created
INFO: ngram_model_arpa.c(556): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 18 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 147
INFO: ngram_search_fwdtree.c(338): after: 18 root, 19 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: cmd_ln.c(691): Parsing command line:
\
-hmm /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k \
-lm languagemodel.lm \
-dict dictionary.dic
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-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
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict dictionary.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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k
-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 languagemodel.lm
-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
-min_endfr 0 0
-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
-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:
\
-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+00
-alpha 0.97 9.700000e-01
-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+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-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+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(246): Parsed model-specific feature parameters from /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices
INFO: acmod.c(121): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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 /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump
INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION
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 4130 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: dictionary.dic
ERROR: "dict.c", line 193: Line 20: Phone 'KNOCK' is mising in the acoustic model; word 'KNOCK' ignored
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 22 words read
INFO: dict.c(341): Reading filler dictionary: /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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=26, 2=24, 3=24
INFO: ngram_model_arpa.c(135): Reading unigrams
INFO: ngram_model_arpa.c(516): 26 = #unigrams created
INFO: ngram_model_arpa.c(195): Reading bigrams
INFO: ngram_model_arpa.c(533): 24 = #bigrams created
INFO: ngram_model_arpa.c(534): 3 = #prob2 entries
INFO: ngram_model_arpa.c(542): 4 = #bo_wt2 entries
INFO: ngram_model_arpa.c(292): Reading trigrams
INFO: ngram_model_arpa.c(555): 24 = #trigrams created
INFO: ngram_model_arpa.c(556): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 21 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 184
INFO: ngram_search_fwdtree.c(338): after: 21 root, 56 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
sh: 1: aplaysay.wav: not found
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm_dmix.c:957:(snd_pcm_dmix_open) The dmix plugin supports only playback stream
Cannot connect to server socket err = No such file or directory
Cannot connect to server request channel
jack server is not running or cannot be started
INFO: cmn.c(175): CMN: 20.31 0.46 4.79 2.74 0.74 1.08 1.03 -1.33 -0.07 0.80 -1.73 1.43 0.18
INFO: ngram_search_fwdtree.c(1549): 1661 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 24373 senones evaluated (152/fr)
INFO: ngram_search_fwdtree.c(1553): 10588 channels searched (66/fr), 2808 1st, 5088 last
INFO: ngram_search_fwdtree.c(1557): 1862 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 1988 candidate words for entering last phone (12/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.43 CPU 0.270 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.51 wall 0.320 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(937): 284 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 477 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(941): 358 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(943): 358 words searched (2/fr)
INFO: ngram_search_fwdflat.c(945): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.13 CPU 0.084 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.14 wall 0.086 xRT
INFO: ngram_search.c(1266): lattice start node <s>.0 end node </s>.60
INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 4 nodes, 2 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(</s>:60:158) = -737056
INFO: ps_lattice.c(1403): Joint P(O,S) = -737056 P(S|O) = 0
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.001 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.003 xRT
===================
JASPER:
===================
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm_dmix.c:957:(snd_pcm_dmix_open) The dmix plugin supports only playback stream
Cannot connect to server socket err = No such file or directory
Cannot connect to server request channel
jack server is not running or cannot be started
INFO: cmn.c(175): CMN: 20.24 0.41 4.98 2.81 0.61 0.95 1.10 -1.15 -0.23 0.76 -1.63 1.57 0.13
INFO: ngram_search_fwdtree.c(1549): 2355 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 34817 senones evaluated (155/fr)
INFO: ngram_search_fwdtree.c(1553): 15130 channels searched (67/fr), 3960 1st, 7331 last
INFO: ngram_search_fwdtree.c(1557): 2630 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 2783 candidate words for entering last phone (12/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.46 CPU 0.206 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 0.48 wall 0.213 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(937): 375 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(939): 669 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(941): 448 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(943): 448 words searched (2/fr)
INFO: ngram_search_fwdflat.c(945): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.05 CPU 0.024 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.05 wall 0.024 xRT
INFO: ngram_search.c(1266): lattice start node <s>.0 end node </s>.98
INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 5 nodes, 2 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(</s>:98:222) = -1019527
INFO: ps_lattice.c(1403): Joint P(O,S) = -1019527 P(S|O) = 0
INFO: ngram_search.c(888): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.001 xRT
===================
JASPER:
===================
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm.c:2217:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm_dmix.c:957:(snd_pcm_dmix_open) The dmix plugin supports only playback stream
Cannot connect to server socket err = No such file or directory
Cannot connect to server request channel
jack server is not running or cannot be started
I pressed ctrl+c at this point as it was just looping
^C
Traceback (most recent call last):
File "jasper.py", line 95, in <module>
app.run()
File "jasper.py", line 71, in run
conversation.handleForever()
File "/root/jasper/client/conversation.py", line 49, in handleForever
threshold, transcribed = self.mic.passiveListen(self.persona)
File "/root/jasper/client/mic.py", line 150, in passiveListen
data = stream.read(CHUNK)
File "/usr/lib/pymodules/python2.7/pyaudio.py", line 564, in read
return pa.read_stream(self._stream, num_frames)
KeyboardInterrupt
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.89 CPU 0.234 xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 0.99 wall 0.259 xRT
INFO: ngram_search_fwdflat.c(174): TOTAL fwdflat 0.19 CPU 0.050 xRT
INFO: ngram_search_fwdflat.c(177): TOTAL fwdflat 0.19 wall 0.050 xRT
INFO: ngram_search.c(317): TOTAL bestpath 0.00 CPU 0.001 xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.01 wall 0.002 xRT
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.00 CPU nan xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 0.00 wall nan xRT
INFO: ngram_search_fwdflat.c(174): TOTAL fwdflat 0.00 CPU nan xRT
INFO: ngram_search_fwdflat.c(177): TOTAL fwdflat 0.00 wall nan xRT
INFO: ngram_search.c(317): TOTAL bestpath 0.00 CPU nan xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 wall nan xRT
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.00 CPU nan xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 0.00 wall nan xRT
INFO: ngram_search_fwdflat.c(174): TOTAL fwdflat 0.00 CPU nan xRT
INFO: ngram_search_fwdflat.c(177): TOTAL fwdflat 0.00 wall nan xRT
INFO: ngram_search.c(317): TOTAL bestpath 0.00 CPU nan xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 wall nan xRT
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.00 CPU nan xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 0.00 wall nan xRT
INFO: ngram_search_fwdflat.c(174): TOTAL fwdflat 0.00 CPU nan xRT
INFO: ngram_search_fwdflat.c(177): TOTAL fwdflat 0.00 wall nan xRT
INFO: ngram_search.c(317): TOTAL bestpath 0.00 CPU nan xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 wall nan xRT
Exception in thread APScheduler (most likely raised during interpreter shutdown):
Traceback (most recent call last):
File "/usr/lib/python2.7/threading.py", line 552, in __bootstrap_inner
File "/usr/lib/python2.7/threading.py", line 505, in run
File "/usr/local/lib/python2.7/dist-packages/apscheduler/scheduler.py", line 579, in _main_loop
<type 'exceptions.AttributeError'>: 'NoneType' object has no attribute 'debug'
Read the README and moved this thread to a google groups post here: https://groups.google.com/forum/#!topic/jasper-support-forum/r6LGDKMPnnY
aplay -l won't list recording devices, but arecord -l will. If card 0, device 0 is not the one you want you may need to fix that. Also I know portaudio (what pyaudio uses) does not automatically convert audio rates (though pyaudio might), so if you request a sample rate the hardware doesn't support it might not work. You could try changing RATE in mic.py to 48000 or 44100. My cmi8768 doesn't support a sample rate of 16000 for recording. alsacap -R will tell you supported rates if you have it installed.
Using dmix/plughw in your asound.conf will take care of sample rate conversions.
I fixed the problem and installed jackd (sudo apt-get install jackd).Then I added this command to my startup programs: jackd -d dummy Now the errors are gone.
How did you do this hmrajas? ecron / cron jobs? What was the command? Then I added this command to my startup programs: jackd -d dummy
I have been trying to get jasper to work on the Beaglebone black, documenting most of my efforts here, including following some of the steps in #34 However, I have gotten stuck on the following
I know that this is just a dependency and not a problem with jasper itself, but I think that someone here may have a clue on how to fix this as I am not quite sure. it does look like quite a convincing compiler version / missing library error though. I am running: