| View previous topic :: View next topic |
| Author |
Message |
G|N|
Tux's lil' helper
Joined: 26 Feb 2004
Posts: 138
Location: Turnhout (Belgium)
|
 Posted: Mon Mar 14, 2005 7:42 pm Post subject: sphix2 + cont_ad_calib failed |
 |
|
when i run sphinx2-simple i get this error and it kills sphinx, really anoying!
| Code: | pc-02 wout # sphinx2-simple
sphinx2-simple:
Demo CMU Sphinx2 decoder called with command line arguments.
<executing /usr/local/bin/sphinx2-continuous, please wait>
/usr/local/bin/sphinx2-continuous \
-live TRUE \
-ctloffset 0 \
-ctlcount 100000000 \
-cepdir /usr/local/share/sphinx2/model/lm/turtle/ctl \
-datadir /usr/local/share/sphinx2/model/lm/turtle/ctl \
-agcemax TRUE \
-langwt 6.5 \
-fwdflatlw 8.5 \
-rescorelw 9.5 \
-ugwt 0.5 \
-fillpen 1e-10 \
-silpen 0.005 \
-inspen 0.65 \
-top 1 \
-topsenfrm 3 \
-topsenthresh \
-70000 \
-beam 2e-06 \
-npbeam 2e-06 \
-lpbeam 2e-05 \
-lponlybeam 0.0005 \
-nwbeam 0.0005 \
-fwdflat FALSE \
-fwdflatbeam 1e-08 \
-fwdflatnwbeam 0.0003 \
-bestpath TRUE \
-kbdumpdir /usr/local/share/sphinx2/model/lm/turtle \
-lmfn /usr/local/share/sphinx2/model/lm/turtle/turtle.lm \
-dictfn /usr/local/share/sphinx2/model/lm/turtle/turtle.dic \
-ndictfn /usr/local/share/sphinx2/model/hmm/6k/noisedict \
-phnfn /usr/local/share/sphinx2/model/hmm/6k/phone \
-mapfn /usr/local/share/sphinx2/model/hmm/6k/map \
-hmmdir /usr/local/share/sphinx2/model/hmm/6k \
-hmmdirlist /usr/local/share/sphinx2/model/hmm/6k \
-8bsen TRUE \
-sendumpfn /usr/local/share/sphinx2/model/hmm/6k/sendump \
-cbdir /usr/local/share/sphinx2/model/hmm/6k
pc-02
Mon Mar 14 20:41:50 CET 2005
INFO: fbs_main.c(1143): libfbs/main COMPILED ON: Mar 14 2005, AT: 20:34:01
INFO: kb_main.c(396): kb_main.c(397): Reading phone file [/usr/local/share/sphinx2/model/hmm/6k/phone]
INFO: phone.c(378): Using 0 phonological mappings
INFO: kb_main.c(406): kb_main.c(406): Reading map file [/usr/local/share/sphinx2/model/hmm/6k/map]
INFO: hmm_tied_r.c(1327): Read Map: 125716 phones map to 23355 unique senone sequences
INFO: kb_main.c(409): kb_main.c(410): Reading dict file [/usr/local/share/sphinx2/model/lm/turtle/turtle.dic]
INFO: dict.c(467): dict_load: first line of /usr/local/share/sphinx2/model/lm/turtle/turtle.dic was A, expecting '!'
INFO: dict.c(469): dict_load: will assume first line contains a word
INFO: dict.c(633): 111 = words in file [/usr/local/share/sphinx2/model/lm/turtle/turtle.dic]
INFO: dict.c(467): dict_load: first line of /usr/local/share/sphinx2/model/hmm/6k/noisedict was ++BREATH++, expecting '!'
INFO: dict.c(469): dict_load: will assume first line contains a word
INFO: dict.c(633): 7 = words in file [/usr/local/share/sphinx2/model/hmm/6k/noisedict]
INFO: dict.c(400): LEFT CONTEXT TABLES
INFO: dict.c(1079): Entry Context table contains
76 entries
INFO: dict.c(1080): 3876 possible cross word triphones.
INFO: dict.c(1116): 3268 triphones
608 pseudo diphones
0 uniphones
INFO: dict.c(1142): Exit Context table contains
76 entries
INFO: dict.c(1143): 3876 possible cross word triphones.
INFO: dict.c(1206): 3268 triphones
608 pseudo diphones
0 uniphones
INFO: dict.c(1208): 1605 right context entries
INFO: dict.c(1209): 21 ave entries per exit context
INFO: dict.c(404): RIGHT CONTEXT TABLES
INFO: dict.c(1079): Entry Context table contains
65 entries
INFO: dict.c(1080): 3315 possible cross word triphones.
INFO: dict.c(1116): 2730 triphones
585 pseudo diphones
0 uniphones
INFO: dict.c(1142): Exit Context table contains
65 entries
INFO: dict.c(1143): 3315 possible cross word triphones.
INFO: dict.c(1206): 2730 triphones
585 pseudo diphones
0 uniphones
INFO: dict.c(1208): 1625 right context entries
INFO: dict.c(1209): 25 ave entries per exit context
INFO: dict.c(408): 0 unique triphones were mapped to ci phones
INFO: lm_3g.c(856): lm_3g.c(856): Reading LM file /usr/local/share/sphinx2/model/lm/turtle/turtle.lm (name "")
INFO: lm_3g.c(887): lm_3g.c(887): ngrams 1=91, 2=212, 3=177
INFO: lm_3g.c(895): lm_3g.c(895): 121 words in dictionary
INFO: lm_3g.c(1412): lm_3g.c(1413): Looking for precompiled LM dump file /usr/local/share/sphinx2/model/lm/turtle/turtle.lm.DMP
INFO: lm_3g.c(1416): lm_3g.c(1417): Precompiled file not found; continue with LM file
INFO: lm_3g.c(548): lm_3g.c(548): Reading unigrams
INFO: lm_3g.c(937): 91 = #unigrams created
INFO: lm_3g.c(593): lm_3g.c(593): Reading bigrams
INFO: lm_3g.c(949):
212 = #bigrams created
INFO: lm_3g.c(950): 20 = #prob2 entries
INFO: lm_3g.c(957): 12 = #bo_wt2 entries
INFO: lm_3g.c(672): lm_3g.c(672): Reading trigrams
INFO: lm_3g.c(966):
177 = #trigrams created
INFO: lm_3g.c(967): 12 = #prob3 entries
INFO: lm_3g.c(1065): lm_3g.c(1066): bo_wt(</s>) changed from -0.3010 to -99.0000INFO: lm_3g.c(1071): lm_3g.c(1072): prob(<s>) changed from -0.9129 to -99.0000
INFO: lm_3g.c(1721): 6.50 = Language Weight
INFO: lm_3g.c(1722): 0.50 = Unigram Weight
INFO: lm_3g.c(1723): -4308 = LOG (Insertion Penalty (0.65))
INFO: lm_3g.c(1215): lm_3g.c(1215): LM("") added
INFO: lm_3g.c(1144): lm_3g.c(1145): Adding 0 initial OOV words to LM
INFO: hmm_tied_r.c(228): hmm_tied_r.c(229): Loading HMMs from dump file /usr/local/share/sphinx2/model/hmm/6k/sendump
INFO: hmm_tied_r.c(239): hmm_tied_r.c(239): BEGIN FILE FORMAT DESCRIPTION
INFO: sc_vq.c(536): SCVQInit: top 1, 6255 models, 1 dist, 0.000100 var floor.
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/cep.256.vec
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/cep.256.var
INFO: sc_vq.c(1576): sc_vq.c(1576): Quantizing senone PDFs to 8 bits
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/d2cep.256.vec
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/d2cep.256.var
INFO: sc_vq.c(1576): sc_vq.c(1576): Quantizing senone PDFs to 8 bits
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/p3cep.256.vec
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/p3cep.256.var
INFO: sc_vq.c(1576): sc_vq.c(1576): Quantizing senone PDFs to 8 bits
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/xcep.256.vec
INFO: cep_rw.c(130): cep_rw.c(130): Byte reversing /usr/local/share/sphinx2/model/hmm/6k/xcep.256.var
INFO: sc_vq.c(1576): sc_vq.c(1576): Quantizing senone PDFs to 8 bits
INFO: search.c(3453): search.c(3453): Estimating maximal search tree
INFO: search.c(3564): search.c(3565): max nonroot chan increased to 337
INFO: search.c(3574): search.c(3575): 73 root, 209 non-root channels, 13 single-phone words
INFO: search.c(1986): search.c(1986): topsen-window = 3, threshold = -70000
INFO: search.c(2874): -1049840 = beam width
INFO: search.c(2883): -608104 = new word beam width
INFO: search.c(2901): -1049840 = new phone beam width
INFO: search.c(2910): -865624 = last phone beam width
INFO: search.c(2892): -608104 = Last phone alone beam width
INFO: search.c(2954): -52986 = LOG (Silence Word Penalty) + LOG (Phone Penalty)
INFO: search.c(2967): -230270 = LOG (Filler Word Penalty) + LOG (Phone Penalty)INFO: search.c(2945): 0 = newword penalty
INFO: search.c(2978): search.c(2979): LW = fwdtree: 6.5, fwdflat: 8.5, bestpath: 9.5
INFO: search.c(4004): search.c(4005): Flat-pass bw = 1.0e-08 (-1473728), nwbw = 3.0e-04 (-648968)
INFO: uttproc.c(969): Will not use double bandwidth in mel filter
INFO: live_norm.c(117): mean[0]= 8.00, mean[1..12]= 0.0
INFO: fsg_search.c(203): FSG(beam: -1049840, pbeam: -1049840, wbeam: -608104; wip: -28002, pip: 0)
INFO: fbs_main.c(987): fbs_main.c(987): Live mode; MeanNorm set to NORM_PRIOR
INFO: search.c(3451): search.c(3451): Creating search tree
INFO: search.c(3574): search.c(3575): 73 root, 209 non-root channels, 13 single-phone words
INFO: uttproc.c(1653): LM= ""
INFO: search.c(2075): search.c(2076): startword= <s> (id= 112)
INFO: fbs_main.c(1286): libfbs/main COMPILED ON: Mar 14 2005, AT: 20:34:01
INFO: tty-continuous.c(221): /usr/local/bin/sphinx2-continuous COMPILED ON: Mar 14 2005, AT: 20:34:39
FATAL_ERROR: "tty-continuous.c", line 120: cont_ad_calib failed
|
does anyone know if there is a solution for this? |
|
| Back to top |
|
 |
glamdringlfo
n00b
Joined: 30 Jul 2003
Posts: 15
Location: Grand Rapids, MI
|
| Posted: Mon May 23, 2005 11:15 pm Post subject: |
|
|
I have the same problem. I don't have a solution yet, but I think it has something to do with access to the microphone. According to the docs, cont_ad_calib is used for getting a sample of background noise to know what to compensate for. I think it's failing to do that for some reason, and so cannot continue. If I find the answer, I'll post it.
Andy |
|
| Back to top |
|
|
|
|
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
|
|
Other Things Gentoo
