Forum Replies Created
Viewing 11 posts - 1 through 11 (of 11 total)
Advertisement: “RuleORama is an OpenEars™ plugin that lets you create rules-based grammars for fixed phrase recognition, fast enough for RapidEars!”
-
AuthorPosts
-
anhtuParticipant
Thanks,
Do you know any framework can help me in this case?
anhtuParticipantI’m sorry. This is my mistake. I dont upgrade OpenEars to version 2.041. The problem is solved. Thank you very much.
anhtuParticipantWell, it is so weird. My co-worker said he updated RapidEars to 2.04.
I will ask him to update and try again. And I will post the result tomorrow also.Thank you.
anhtuParticipantHere is the contents:crash when came to letter D
.dic file
D D IY.arpa file
############################################################################# ## Copyright (c) 1996, Carnegie Mellon University, Cambridge University, ## Ronald Rosenfeld and Philip Clarkson ## Version 3, Copyright (c) 2006, Carnegie Mellon University ## Contributors includes Wen Xu, Ananlada Chotimongkol, ## David Huggins-Daines, Arthur Chan and Alan Black ############################################################################# ============================================================================= =============== This file was produced by the CMU-Cambridge =============== =============== Statistical Language Modeling Toolkit =============== ============================================================================= This is a 3-gram language model, based on a vocabulary of 3 words, which begins "</s>", "<s>", "D"... This is a CLOSED-vocabulary model (OOVs eliminated from training data and are forbidden in test data) Witten Bell discounting was applied. This file is in the ARPA-standard format introduced by Doug Paul. p(wd3|wd1,wd2)= if(trigram exists) p_3(wd1,wd2,wd3) else if(bigram w1,w2 exists) bo_wt_2(w1,w2)*p(wd3|wd2) else p(wd3|w2) p(wd2|wd1)= if(bigram exists) p_2(wd1,wd2) else bo_wt_1(wd1)*p_1(wd2) All probs and back-off weights (bo_wt) are given in log10 form. Data formats: Beginning of data mark: \data\ ngram 1=nr # number of 1-grams ngram 2=nr # number of 2-grams ngram 3=nr # number of 3-grams \1-grams: p_1 wd_1 bo_wt_1 \2-grams: p_2 wd_1 wd_2 bo_wt_2 \3-grams: p_3 wd_1 wd_2 wd_3 end of data mark: \end\ \data\ ngram 1=3 ngram 2=2 ngram 3=1 \1-grams: -98.6990 </s> 0.0000 -98.6990 <s> -99.9990 0.0000 D -0.3010 \2-grams: -0.3010 <s> D 0.0000 -0.3010 D </s> -0.3010 \3-grams: -0.3010 <s> D </s> \end\the log:
2015-08-04 17:18:43.475 App_Name[50827:4272534] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-04 17:18:43.525 App_Name[50827:4272534] Starting dynamic language model generation 2015-08-04 17:18:43.647 App_Name[50827:4272534] Done creating language model with CMUCLMTK in 0.122107 seconds. 2015-08-04 17:18:43.669 App_Name[50827:4272534] I'm done running performDictionaryLookup and it took 0.000215 seconds 2015-08-04 17:18:43.677 App_Name[50827:4272534] I'm done running dynamic language model generation and it took 0.196122 seconds 2015-08-04 17:18:43.678 App_Name[50827:4272534] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-04 17:18:43.685 App_Name[50827:4272534] cocos2d: surface size: 2048x1536 2015-08-04 17:18:44.690 App_Name[50827:4272534] User gave mic permission for this app. 2015-08-04 17:18:44.691 App_Name[50827:4272534] Valid setSecondsOfSilence value of 0.200000 will be used. 2015-08-04 17:18:44.692 App_Name[50827:4273012] Starting listening. 2015-08-04 17:18:44.692 App_Name[50827:4273012] about to set up audio session 2015-08-04 17:18:44.842 App_Name[50827:4272710] Audio route has changed for the following reason: 2015-08-04 17:18:44.846 App_Name[50827:4272710] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord 2015-08-04 17:18:44.852 App_Name[50827:4272710] This is not a case in which OpenEars notifies of a route change. At the close of this function, the new audio route is ---SpeakerMicrophoneBuiltIn---. The previous route before changing to this route was <AVAudioSessionRouteDescription: 0x170806470, inputs = (null); outputs = ( "<AVAudioSessionPortDescription: 0x17080b520, type = Speaker; name = Speaker; UID = Built-In Speaker; selectedDataSource = (null)>" )>. 2015-08-04 17:18:44.866 App_Name[50827:4273012] done starting audio unit INFO: cmd_ln.c(702): Parsing command line: \ -lm /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_A_0.DMP \ -vad_prespeech 10 \ -vad_postspeech 20 \ -vad_threshold 2.000000 \ -remove_noise yes \ -remove_silence yes \ -bestpath yes \ -lw 6.500000 \ -dict /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_A_0.dic \ -hmm /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle 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 -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 /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_A_0.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 /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle -input_endian little little -jsgf -kdmaxbbi -1 -1 -kdmaxdepth 0 0 -kdtree -keyphrase -kws -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lextreedump 0 0 -lifter 0 0 -lm /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_A_0.DMP -lmctl -lmname -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 10000 10000 -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 -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 legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -usewdphones no no -uw 1.0 1.000000e+00 -vad_postspeech 50 20 -vad_prespeech 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: cmd_ln.c(702): Parsing command line: \ -nfilt 25 \ -lowerf 130 \ -upperf 6800 \ -feat 1s_c_d_dd \ -svspec 0-12/13-25/26-38 \ -agc none \ -cmn current \ -varnorm no \ -transform dct \ -lifter 22 \ -cmninit 40 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 40 -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 22 -logspec no no -lowerf 133.33334 1.300000e+02 -ncep 13 13 -nfft 512 512 -nfilt 40 25 -remove_dc no no -remove_noise yes yes -remove_silence yes yes -round_filters yes yes -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 6.800000e+03 -vad_postspeech 50 20 -vad_prespeech 10 10 -vad_threshold 2.0 2.000000e+00 -varnorm no no -verbose no no -warp_params -warp_type inverse_linear inverse_linear -wlen 0.025625 2.562500e-02 INFO: acmod.c(252): Parsed model-specific feature parameters from /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/feat.params 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(171): Using subvector specification 0-12/13-25/26-38 INFO: mdef.c(518): Reading model definition: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/mdef INFO: mdef.c(531): Found byte-order mark BMDF, assuming this is a binary mdef file INFO: bin_mdef.c(336): Reading binary model definition: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/mdef INFO: bin_mdef.c(516): 46 CI-phone, 168344 CD-phone, 3 emitstate/phone, 138 CI-sen, 6138 Sen, 32881 Sen-Seq INFO: tmat.c(206): Reading HMM transition probability matrices: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/transition_matrices INFO: acmod.c(124): Attempting to use SCHMM computation module INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/means INFO: ms_gauden.c(292): 1 codebook, 3 feature, size: INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/variances INFO: ms_gauden.c(292): 1 codebook, 3 feature, size: INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(354): 0 variance values floored INFO: s2_semi_mgau.c(904): Loading senones from dump file /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/sendump INFO: s2_semi_mgau.c(928): BEGIN FILE FORMAT DESCRIPTION INFO: s2_semi_mgau.c(991): Rows: 512, Columns: 6138 INFO: s2_semi_mgau.c(1023): Using memory-mapped I/O for senones INFO: s2_semi_mgau.c(1294): Maximum top-N: 4 Top-N beams: 0 0 0 INFO: dict.c(320): Allocating 4107 * 32 bytes (128 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_A_0.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 2 words read INFO: dict.c(342): Reading filler dictionary: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(345): 9 words read INFO: dict2pid.c(396): Building PID tables for dictionary INFO: dict2pid.c(406): Allocating 46^3 * 2 bytes (190 KiB) for word-initial triphones INFO: dict2pid.c(132): Allocated 51152 bytes (49 KiB) for word-final triphones INFO: dict2pid.c(196): Allocated 51152 bytes (49 KiB) for single-phone word triphones INFO: ngram_model_arpa.c(79): No \data\ mark in LM file INFO: ngram_model_dmp.c(166): Will use memory-mapped I/O for LM file INFO: ngram_model_dmp.c(220): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_dmp.c(266): 3 = LM.unigrams(+trailer) read INFO: ngram_model_dmp.c(312): 2 = LM.bigrams(+trailer) read INFO: ngram_model_dmp.c(338): 1 = LM.trigrams read INFO: ngram_model_dmp.c(363): 2 = LM.prob2 entries read INFO: ngram_model_dmp.c(383): 3 = LM.bo_wt2 entries read INFO: ngram_model_dmp.c(403): 2 = LM.prob3 entries read INFO: ngram_model_dmp.c(431): 1 = LM.tseg_base entries read INFO: ngram_model_dmp.c(487): 3 = ascii word strings read INFO: ngram_search_fwdtree.c(99): 0 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 12 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 12 single-phone words INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 128 ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 11 single-phone words INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25 2015-08-04 17:18:44.981 App_Name[50827:4273012] Restoring SmartCMN value of 55.322021 2015-08-04 17:18:44.982 App_Name[50827:4273012] Listening. 2015-08-04 17:18:44.982 App_Name[50827:4273012] Project has these words or phrases in its dictionary: A A(2) 2015-08-04 17:18:44.983 App_Name[50827:4273012] Recognition loop has started 2015-08-04 17:18:44.987 App_Name[50827:4272534] Pocketsphinx is now listening. 2015-08-04 17:18:45.589 App_Name[50827:4273012] Speech detected... 2015-08-04 17:18:45.591 App_Name[50827:4273012] Pocketsphinx heard "" with a score of (-1841) and an utterance ID of 0. 2015-08-04 17:18:45.673 App_Name[50827:4273012] Pocketsphinx heard "" with a score of (-4145) and an utterance ID of 1. 2015-08-04 17:18:45.776 App_Name[50827:4273012] End of speech detected... INFO: cmn_prior.c(131): cmn_prior_update: from < 55.32 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 > INFO: cmn_prior.c(149): cmn_prior_update: to < 50.10 -2.86 -21.38 6.18 9.53 9.65 -6.16 1.99 -5.67 -2.94 -0.32 -7.97 -8.61 > INFO: ngram_search_fwdtree.c(1550): 344 words recognized (9/fr) INFO: ngram_search_fwdtree.c(1552): 1104 senones evaluated (30/fr) INFO: ngram_search_fwdtree.c(1556): 366 channels searched (9/fr), 0 1st, 366 last INFO: ngram_search_fwdtree.c(1559): 366 words for which last channels evaluated (9/fr) INFO: ngram_search_fwdtree.c(1561): 0 candidate words for entering last phone (0/fr) INFO: ngram_search_fwdtree.c(1564): fwdtree 0.09 CPU 0.251 xRT INFO: ngram_search_fwdtree.c(1567): fwdtree 0.51 wall 1.383 xRT INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words INFO: ngram_search_fwdflat.c(938): 230 words recognized (6/fr) INFO: ngram_search_fwdflat.c(940): 720 senones evaluated (19/fr) INFO: ngram_search_fwdflat.c(942): 267 channels searched (7/fr) INFO: ngram_search_fwdflat.c(944): 267 words searched (7/fr) INFO: ngram_search_fwdflat.c(947): 62 word transitions (1/fr) INFO: ngram_search_fwdflat.c(950): fwdflat 0.00 CPU 0.010 xRT INFO: ngram_search_fwdflat.c(953): fwdflat 0.00 wall 0.009 xRT INFO: ngram_search.c(1215): </s> not found in last frame, using <sil>.35 instead INFO: ngram_search.c(1268): lattice start node <s>.0 end node <sil>.2 INFO: ngram_search.c(1294): Eliminated 90 nodes before end node INFO: ngram_search.c(1399): Lattice has 92 nodes, 1 links INFO: ps_lattice.c(1368): Normalizer P(O) = alpha(<sil>:2:35) = -4823285 INFO: ps_lattice.c(1403): Joint P(O,S) = -4823286 P(S|O) = -1 INFO: ngram_search.c(890): bestpath 0.00 CPU 0.000 xRT INFO: ngram_search.c(893): bestpath 0.00 wall 0.001 xRT 2015-08-04 17:18:45.781 App_Name[50827:4273012] Pocketsphinx heard "" with a score of (-47303) and an utterance ID of 2. 2015-08-04 17:18:45.782 App_Name[50827:4273012] Hypothesis was null so we aren't returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController's property returnNullHypotheses to TRUE before starting OEPocketsphinxController. 2015-08-04 17:18:46.052 App_Name[50827:4273012] Speech detected... 2015-08-04 17:18:46.053 App_Name[50827:4273012] Pocketsphinx heard "" with a score of (-3968) and an utterance ID of 3. 2015-08-04 17:18:46.165 App_Name[50827:4273012] Pocketsphinx heard "A" with a score of (-5233) and an utterance ID of 4. 2015-08-04 17:18:46.173 App_Name[50827:4272534] rapidEarsDidReceiveFinishedSpeechHypothesis: A with score: -5233 2015-08-04 17:18:46.174 App_Name[50827:4272534] Play effect sound 2015-08-04 17:18:49.159 App_Name[50827:4272534] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-04 17:18:49.172 App_Name[50827:4272534] Starting dynamic language model generation INFO: cmd_ln.c(702): Parsing command line: sphinx_lm_convert \ -i /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.arpa \ -o /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.DMP Current configuration: [NAME] [DEFLT] [VALUE] -case -debug 0 -help no no -i /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.arpa -ienc -ifmt -logbase 1.0001 1.000100e+00 -mmap no no -o /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.DMP -oenc utf8 utf8 -ofmt INFO: ngram_model_arpa.c(504): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_arpa.c(137): Reading unigrams INFO: ngram_model_arpa.c(543): 3 = #unigrams created INFO: ngram_model_arpa.c(197): Reading bigrams INFO: ngram_model_arpa.c(561): 2 = #bigrams created INFO: ngram_model_arpa.c(562): 2 = #prob2 entries INFO: ngram_model_arpa.c(570): 3 = #bo_wt2 entries INFO: ngram_model_arpa.c(294): Reading trigrams INFO: ngram_model_arpa.c(583): 1 = #trigrams created INFO: ngram_model_arpa.c(584): 2 = #prob3 entries INFO: ngram_model_dmp.c(518): Building DMP model... INFO: ngram_model_dmp.c(548): 3 = #unigrams created INFO: ngram_model_dmp.c(649): 2 = #bigrams created INFO: ngram_model_dmp.c(650): 2 = #prob2 entries INFO: ngram_model_dmp.c(657): 3 = #bo_wt2 entries INFO: ngram_model_dmp.c(661): 1 = #trigrams created INFO: ngram_model_dmp.c(662): 2 = #prob3 entries 2015-08-04 17:18:49.299 App_Name[50827:4272534] Done creating language model with CMUCLMTK in 0.126771 seconds. 2015-08-04 17:18:49.307 App_Name[50827:4272534] I'm done running performDictionaryLookup and it took 0.002471 seconds 2015-08-04 17:18:49.317 App_Name[50827:4272534] I'm done running dynamic language model generation and it took 0.157271 seconds 2015-08-04 17:18:49.318 App_Name[50827:4272534] Valid setSecondsOfSilence value of 0.200000 will be used. INFO: cmn_prior.c(131): cmn_prior_update: from < 50.10 -2.86 -21.38 6.18 9.53 9.65 -6.16 1.99 -5.67 -2.94 -0.32 -7.97 -8.61 > INFO: cmn_prior.c(149): cmn_prior_update: to < 56.52 4.14 -13.40 9.27 -0.63 2.79 -13.06 -7.02 -0.07 -7.23 -1.33 -5.36 -9.11 > INFO: ngram_search_fwdtree.c(1550): 344 words recognized (9/fr) INFO: ngram_search_fwdtree.c(1552): 1131 senones evaluated (31/fr) INFO: ngram_search_fwdtree.c(1556): 366 channels searched (9/fr), 0 1st, 366 last INFO: ngram_search_fwdtree.c(1559): 366 words for which last channels evaluated (9/fr) INFO: ngram_search_fwdtree.c(1561): 0 candidate words for entering last phone (0/fr) INFO: ngram_search_fwdtree.c(1564): fwdtree 0.82 CPU 2.215 xRT INFO: ngram_search_fwdtree.c(1567): fwdtree 3.71 wall 10.024 xRT INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 4 words INFO: ngram_search_fwdflat.c(938): 302 words recognized (8/fr) INFO: ngram_search_fwdflat.c(940): 1162 senones evaluated (31/fr) INFO: ngram_search_fwdflat.c(942): 387 channels searched (10/fr) INFO: ngram_search_fwdflat.c(944): 387 words searched (10/fr) INFO: ngram_search_fwdflat.c(947): 134 word transitions (3/fr) INFO: ngram_search_fwdflat.c(950): fwdflat 0.00 CPU 0.009 xRT INFO: ngram_search_fwdflat.c(953): fwdflat 0.00 wall 0.010 xRT 2015-08-04 17:18:49.495 App_Name[50827:4273056] there is a request to change to the language model file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.DMP 2015-08-04 17:18:49.496 App_Name[50827:4273056] The language model ID is 1438683529 INFO: cmd_ln.c(702): Parsing command line: 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 -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 -input_endian little little -jsgf -kdmaxbbi -1 -1 -kdmaxdepth 0 0 -kdtree -keyphrase -kws -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lextreedump 0 0 -lifter 0 0 -lm -lmctl -lmname -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 10000 10000 -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 -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 legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -usewdphones no no -uw 1.0 1.000000e+00 -vad_postspeech 50 50 -vad_prespeech 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: dict.c(320): Allocating 4106 * 32 bytes (128 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 1 words read INFO: dict.c(342): Reading filler dictionary: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(345): 9 words read INFO: dict2pid.c(396): Building PID tables for dictionary INFO: dict2pid.c(406): Allocating 46^3 * 2 bytes (190 KiB) for word-initial triphones INFO: dict2pid.c(132): Allocated 51152 bytes (49 KiB) for word-final triphones INFO: dict2pid.c(196): Allocated 51152 bytes (49 KiB) for single-phone word triphones INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 9 single-phone words 2015-08-04 17:18:49.515 App_Name[50827:4273056] Success loading the specified dictionary file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.dic. INFO: ngram_model_arpa.c(79): No \data\ mark in LM file INFO: ngram_model_dmp.c(166): Will use memory-mapped I/O for LM file INFO: ngram_model_dmp.c(220): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_dmp.c(266): 3 = LM.unigrams(+trailer) read INFO: ngram_model_dmp.c(312): 2 = LM.bigrams(+trailer) read INFO: ngram_model_dmp.c(338): 1 = LM.trigrams read INFO: ngram_model_dmp.c(363): 2 = LM.prob2 entries read INFO: ngram_model_dmp.c(383): 3 = LM.bo_wt2 entries read INFO: ngram_model_dmp.c(403): 2 = LM.prob3 entries read INFO: ngram_model_dmp.c(431): 1 = LM.tseg_base entries read INFO: ngram_model_dmp.c(487): 3 = ascii word strings read INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 128 INFO: ngram_search_fwdtree.c(339): after: 1 root, 0 non-root channels, 9 single-phone words INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25 2015-08-04 17:18:49.518 App_Name[50827:4273056] Success loading the specified language model file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.DMP. 2015-08-04 17:18:49.518 App_Name[50827:4272534] Pocketsphinx is now using the following language model: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.DMP and the following dictionary: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_B_1.dic 2015-08-04 17:18:49.519 App_Name[50827:4273056] Changed language model. Project has these words or phrases in its dictionary: B INFO: cmn_prior.c(131): cmn_prior_update: from < 56.52 4.14 -13.40 9.27 -0.63 2.79 -13.06 -7.02 -0.07 -7.23 -1.33 -5.36 -9.11 > INFO: cmn_prior.c(149): cmn_prior_update: to < 56.52 4.14 -13.40 9.27 -0.63 2.79 -13.06 -7.02 -0.07 -7.23 -1.33 -5.36 -9.11 > INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 0 words 2015-08-04 17:18:49.744 App_Name[50827:4273056] Speech detected... 2015-08-04 17:18:49.745 App_Name[50827:4273056] Pocketsphinx heard "" with a score of (-2471) and an utterance ID of 5. 2015-08-04 17:18:49.745 App_Name[50827:4273056] Hypothesis was null so we aren't returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController's property returnNullHypotheses to TRUE before starting OEPocketsphinxController. 2015-08-04 17:18:49.875 App_Name[50827:4273056] Pocketsphinx heard "" with a score of (-3611) and an utterance ID of 6. 2015-08-04 17:18:50.015 App_Name[50827:4273056] Pocketsphinx heard "" with a score of (-6506) and an utterance ID of 7. 2015-08-04 17:18:50.134 App_Name[50827:4273056] Pocketsphinx heard "" with a score of (-7907) and an utterance ID of 8. 2015-08-04 17:18:50.261 App_Name[50827:4273056] Pocketsphinx heard "" with a score of (-9050) and an utterance ID of 9. 2015-08-04 17:18:50.383 App_Name[50827:4273056] End of speech detected... INFO: cmn_prior.c(131): cmn_prior_update: from < 56.52 4.14 -13.40 9.27 -0.63 2.79 -13.06 -7.02 -0.07 -7.23 -1.33 -5.36 -9.11 > INFO: cmn_prior.c(149): cmn_prior_update: to < 57.29 5.73 -11.50 8.72 -0.13 7.50 -5.11 -8.93 -2.48 -6.79 -6.31 -2.05 -8.11 > INFO: ngram_search_fwdtree.c(1550): 575 words recognized (8/fr) INFO: ngram_search_fwdtree.c(1552): 4967 senones evaluated (72/fr) INFO: ngram_search_fwdtree.c(1556): 2542 channels searched (36/fr), 65 1st, 2477 last INFO: ngram_search_fwdtree.c(1559): 617 words for which last channels evaluated (8/fr) INFO: ngram_search_fwdtree.c(1561): 63 candidate words for entering last phone (0/fr) INFO: ngram_search_fwdtree.c(1564): fwdtree 0.14 CPU 0.201 xRT INFO: ngram_search_fwdtree.c(1567): fwdtree 0.86 wall 1.252 xRT INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 3 words INFO: ngram_search_fwdflat.c(938): 491 words recognized (7/fr) INFO: ngram_search_fwdflat.c(940): 4890 senones evaluated (71/fr) INFO: ngram_search_fwdflat.c(942): 2482 channels searched (35/fr) INFO: ngram_search_fwdflat.c(944): 622 words searched (9/fr) INFO: ngram_search_fwdflat.c(947): 130 word transitions (1/fr) INFO: ngram_search_fwdflat.c(950): fwdflat 0.01 CPU 0.017 xRT INFO: ngram_search_fwdflat.c(953): fwdflat 0.01 wall 0.013 xRT INFO: ngram_search.c(1215): </s> not found in last frame, using B.67 instead INFO: ngram_search.c(1268): lattice start node <s>.0 end node B.55 INFO: ngram_search.c(1294): Eliminated 4 nodes before end node INFO: ngram_search.c(1399): Lattice has 182 nodes, 1073 links INFO: ps_lattice.c(1368): Normalizer P(O) = alpha(B:55:67) = -541208 INFO: ps_lattice.c(1403): Joint P(O,S) = -541660 P(S|O) = -452 INFO: ngram_search.c(890): bestpath 0.00 CPU 0.003 xRT INFO: ngram_search.c(893): bestpath 0.00 wall 0.003 xRT 2015-08-04 17:18:50.395 App_Name[50827:4273056] Pocketsphinx heard "B" with a score of (-10515) and an utterance ID of 10. 2015-08-04 17:18:50.397 App_Name[50827:4272534] rapidEarsDidReceiveFinishedSpeechHypothesis: B with score: -10515 2015-08-04 17:18:50.397 App_Name[50827:4272534] Play effect sound 2015-08-04 17:18:52.427 App_Name[50827:4272534] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-04 17:18:52.438 App_Name[50827:4272534] Starting dynamic language model generation INFO: cmd_ln.c(702): Parsing command line: sphinx_lm_convert \ -i /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.arpa \ -o /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.DMP Current configuration: [NAME] [DEFLT] [VALUE] -case -debug 0 -help no no -i /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.arpa -ienc -ifmt -logbase 1.0001 1.000100e+00 -mmap no no -o /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.DMP -oenc utf8 utf8 -ofmt INFO: ngram_model_arpa.c(504): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_arpa.c(137): Reading unigrams INFO: ngram_model_arpa.c(543): 3 = #unigrams created INFO: ngram_model_arpa.c(197): Reading bigrams INFO: ngram_model_arpa.c(561): 2 = #bigrams created INFO: ngram_model_arpa.c(562): 2 = #prob2 entries INFO: ngram_model_arpa.c(570): 3 = #bo_wt2 entries INFO: ngram_model_arpa.c(294): Reading trigrams INFO: ngram_model_arpa.c(583): 1 = #trigrams created INFO: ngram_model_arpa.c(584): 2 = #prob3 entries INFO: ngram_model_dmp.c(518): Building DMP model... INFO: ngram_model_dmp.c(548): 3 = #unigrams created INFO: ngram_model_dmp.c(649): 2 = #bigrams created INFO: ngram_model_dmp.c(650): 2 = #prob2 entries INFO: ngram_model_dmp.c(657): 3 = #bo_wt2 entries INFO: ngram_model_dmp.c(661): 1 = #trigrams created INFO: ngram_model_dmp.c(662): 2 = #prob3 entries 2015-08-04 17:18:52.554 App_Name[50827:4272534] Done creating language model with CMUCLMTK in 0.115380 seconds. 2015-08-04 17:18:52.579 App_Name[50827:4272534] I'm done running performDictionaryLookup and it took 0.004318 seconds 2015-08-04 17:18:52.587 App_Name[50827:4272534] I'm done running dynamic language model generation and it took 0.159274 seconds 2015-08-04 17:18:52.587 App_Name[50827:4272534] Valid setSecondsOfSilence value of 0.200000 will be used. INFO: cmn_prior.c(131): cmn_prior_update: from < 57.29 5.73 -11.50 8.72 -0.13 7.50 -5.11 -8.93 -2.48 -6.79 -6.31 -2.05 -8.11 > INFO: cmn_prior.c(149): cmn_prior_update: to < 57.29 5.73 -11.50 8.72 -0.13 7.50 -5.11 -8.93 -2.48 -6.79 -6.31 -2.05 -8.11 > INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 0 words 2015-08-04 17:18:52.692 App_Name[50827:4273056] there is a request to change to the language model file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.DMP 2015-08-04 17:18:52.693 App_Name[50827:4273056] The language model ID is 1438683532 INFO: cmd_ln.c(702): Parsing command line: 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 -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 -input_endian little little -jsgf -kdmaxbbi -1 -1 -kdmaxdepth 0 0 -kdtree -keyphrase -kws -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lextreedump 0 0 -lifter 0 0 -lm -lmctl -lmname -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 10000 10000 -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 -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 legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -usewdphones no no -uw 1.0 1.000000e+00 -vad_postspeech 50 50 -vad_prespeech 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: dict.c(320): Allocating 4106 * 32 bytes (128 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 1 words read INFO: dict.c(342): Reading filler dictionary: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(345): 9 words read INFO: dict2pid.c(396): Building PID tables for dictionary INFO: dict2pid.c(406): Allocating 46^3 * 2 bytes (190 KiB) for word-initial triphones INFO: dict2pid.c(132): Allocated 51152 bytes (49 KiB) for word-final triphones INFO: dict2pid.c(196): Allocated 51152 bytes (49 KiB) for single-phone word triphones INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 9 single-phone words INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 9 single-phone words 2015-08-04 17:18:52.711 App_Name[50827:4273056] Success loading the specified dictionary file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.dic. INFO: ngram_model_arpa.c(79): No \data\ mark in LM file INFO: ngram_model_dmp.c(166): Will use memory-mapped I/O for LM file INFO: ngram_model_dmp.c(220): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_dmp.c(266): 3 = LM.unigrams(+trailer) read INFO: ngram_model_dmp.c(312): 2 = LM.bigrams(+trailer) read INFO: ngram_model_dmp.c(338): 1 = LM.trigrams read INFO: ngram_model_dmp.c(363): 2 = LM.prob2 entries read INFO: ngram_model_dmp.c(383): 3 = LM.bo_wt2 entries read INFO: ngram_model_dmp.c(403): 2 = LM.prob3 entries read INFO: ngram_model_dmp.c(431): 1 = LM.tseg_base entries read INFO: ngram_model_dmp.c(487): 3 = ascii word strings read INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 128 INFO: ngram_search_fwdtree.c(339): after: 1 root, 0 non-root channels, 9 single-phone words INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25 2015-08-04 17:18:52.713 App_Name[50827:4273056] Success loading the specified language model file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.DMP. 2015-08-04 17:18:52.714 App_Name[50827:4273056] Changed language model. Project has these words or phrases in its dictionary: C INFO: cmn_prior.c(131): cmn_prior_update: from < 57.29 5.73 -11.50 8.72 -0.13 7.50 -5.11 -8.93 -2.48 -6.79 -6.31 -2.05 -8.11 > INFO: cmn_prior.c(149): cmn_prior_update: to < 57.29 5.73 -11.50 8.72 -0.13 7.50 -5.11 -8.93 -2.48 -6.79 -6.31 -2.05 -8.11 > INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 0 words 2015-08-04 17:18:52.724 App_Name[50827:4272534] Pocketsphinx is now using the following language model: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.DMP and the following dictionary: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_C_2.dic 2015-08-04 17:18:52.829 App_Name[50827:4273056] Speech detected... 2015-08-04 17:18:52.830 App_Name[50827:4273056] Pocketsphinx heard "" with a score of (-3821) and an utterance ID of 11. 2015-08-04 17:18:52.950 App_Name[50827:4273056] Pocketsphinx heard "" with a score of (-4873) and an utterance ID of 12. 2015-08-04 17:18:53.070 App_Name[50827:4273056] End of speech detected... INFO: cmn_prior.c(131): cmn_prior_update: from < 57.29 5.73 -11.50 8.72 -0.13 7.50 -5.11 -8.93 -2.48 -6.79 -6.31 -2.05 -8.11 > INFO: cmn_prior.c(149): cmn_prior_update: to < 58.03 3.50 -9.27 6.71 -0.63 7.91 -2.92 -6.81 -2.32 -6.02 -8.06 -2.33 -7.31 > INFO: ngram_search_fwdtree.c(1550): 290 words recognized (8/fr) INFO: ngram_search_fwdtree.c(1552): 2547 senones evaluated (73/fr) INFO: ngram_search_fwdtree.c(1556): 1181 channels searched (33/fr), 31 1st, 1150 last INFO: ngram_search_fwdtree.c(1559): 310 words for which last channels evaluated (8/fr) INFO: ngram_search_fwdtree.c(1561): 29 candidate words for entering last phone (0/fr) INFO: ngram_search_fwdtree.c(1564): fwdtree 0.06 CPU 0.177 xRT INFO: ngram_search_fwdtree.c(1567): fwdtree 0.36 wall 1.018 xRT INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 3 words INFO: ngram_search_fwdflat.c(938): 242 words recognized (7/fr) INFO: ngram_search_fwdflat.c(940): 2652 senones evaluated (76/fr) INFO: ngram_search_fwdflat.c(942): 1228 channels searched (35/fr) INFO: ngram_search_fwdflat.c(944): 329 words searched (9/fr) INFO: ngram_search_fwdflat.c(947): 91 word transitions (2/fr) INFO: ngram_search_fwdflat.c(950): fwdflat 0.00 CPU 0.013 xRT INFO: ngram_search_fwdflat.c(953): fwdflat 0.00 wall 0.013 xRT INFO: ngram_search.c(1215): </s> not found in last frame, using C.33 instead INFO: ngram_search.c(1268): lattice start node <s>.0 end node C.26 INFO: ngram_search.c(1294): Eliminated 9 nodes before end node INFO: ngram_search.c(1399): Lattice has 61 nodes, 198 links INFO: ps_lattice.c(1368): Normalizer P(O) = alpha(C:26:33) = -297153 INFO: ps_lattice.c(1403): Joint P(O,S) = -297589 P(S|O) = -436 INFO: ngram_search.c(890): bestpath 0.00 CPU 0.002 xRT INFO: ngram_search.c(893): bestpath 0.00 wall 0.002 xRT 2015-08-04 17:18:53.080 App_Name[50827:4273056] Pocketsphinx heard "C" with a score of (-5748) and an utterance ID of 13. 2015-08-04 17:18:53.090 App_Name[50827:4272534] rapidEarsDidReceiveFinishedSpeechHypothesis: C with score: -5748 2015-08-04 17:18:53.091 App_Name[50827:4272534] Play effect sound 2015-08-04 17:18:55.093 App_Name[50827:4272534] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-04 17:18:55.104 App_Name[50827:4272534] Starting dynamic language model generation INFO: cmd_ln.c(702): Parsing command line: sphinx_lm_convert \ -i /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_D_3.arpa \ -o /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_D_3.DMP Current configuration: [NAME] [DEFLT] [VALUE] -case -debug 0 -help no no -i /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_D_3.arpa -ienc -ifmt -logbase 1.0001 1.000100e+00 -mmap no no -o /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_D_3.DMP -oenc utf8 utf8 -ofmt INFO: ngram_model_arpa.c(504): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_arpa.c(137): Reading unigrams INFO: ngram_model_arpa.c(543): 3 = #unigrams created INFO: ngram_model_arpa.c(197): Reading bigrams INFO: ngram_model_arpa.c(561): 2 = #bigrams created INFO: ngram_model_arpa.c(562): 2 = #prob2 entries INFO: ngram_model_arpa.c(570): 3 = #bo_wt2 entries INFO: ngram_model_arpa.c(294): Reading trigrams INFO: ngram_model_arpa.c(583): 1 = #trigrams created INFO: ngram_model_arpa.c(584): 2 = #prob3 entries INFO: ngram_model_dmp.c(518): Building DMP model... INFO: ngram_model_dmp.c(548): 3 = #unigrams created INFO: ngram_model_dmp.c(649): 2 = #bigrams created INFO: ngram_model_dmp.c(650): 2 = #prob2 entries INFO: ngram_model_dmp.c(657): 3 = #bo_wt2 entries INFO: ngram_model_dmp.c(661): 1 = #trigrams created INFO: ngram_model_dmp.c(662): 2 = #prob3 entries 2015-08-04 17:18:55.224 App_Name[50827:4272534] Done creating language model with CMUCLMTK in 0.119595 seconds. 2015-08-04 17:18:55.236 App_Name[50827:4272534] I'm done running performDictionaryLookup and it took 0.006811 seconds 2015-08-04 17:18:55.245 App_Name[50827:4272534] I'm done running dynamic language model generation and it took 0.150872 seconds 2015-08-04 17:18:55.246 App_Name[50827:4272534] Valid setSecondsOfSilence value of 0.200000 will be used. INFO: cmn_prior.c(131): cmn_prior_update: from < 58.03 3.50 -9.27 6.71 -0.63 7.91 -2.92 -6.81 -2.32 -6.02 -8.06 -2.33 -7.31 > INFO: cmn_prior.c(149): cmn_prior_update: to < 58.03 3.50 -9.27 6.71 -0.63 7.91 -2.92 -6.81 -2.32 -6.02 -8.06 -2.33 -7.31 > INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 0 words 2015-08-04 17:18:55.376 App_Name[50827:4273012] there is a request to change to the language model file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_D_3.DMP 2015-08-04 17:18:55.377 App_Name[50827:4273012] The language model ID is 1438683535 INFO: cmd_ln.c(702): Parsing command line: 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 -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 -input_endian little little -jsgf -kdmaxbbi -1 -1 -kdmaxdepth 0 0 -kdtree -keyphrase -kws -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lextreedump 0 0 -lifter 0 0 -lm -lmctl -lmname -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 10000 10000 -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 -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 legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -usewdphones no no -uw 1.0 1.000000e+00 -vad_postspeech 50 50 -vad_prespeech 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: dict.c(320): Allocating 4106 * 32 bytes (128 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_D_3.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 1 words read INFO: dict.c(342): Reading filler dictionary: /private/var/mobile/Containers/Bundle/Application/54D4920A-C3CD-4480-94F2-8654421B4D13/App_Name.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(345): 9 words read INFO: dict2pid.c(396): Building PID tables for dictionary INFO: dict2pid.c(406): Allocating 46^3 * 2 bytes (190 KiB) for word-initial triphones INFO: dict2pid.c(132): Allocated 51152 bytes (49 KiB) for word-final triphones INFO: dict2pid.c(196): Allocated 51152 bytes (49 KiB) for single-phone word triphones INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 9 single-phone words INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 9 single-phone words INFO: ngram_search_fwdtree.c(99): 1 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 10 single-phone words ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 9 single-phone words 2015-08-04 17:18:55.393 App_Name[50827:4273012] Success loading the specified dictionary file /var/mobile/Containers/Data/Application/AE23615A-AB76-4AC4-98BB-0F72F026A2DB/Library/Caches/lession_vocal_D_3.dic. INFO: ngram_model_arpa.c(79): No \data\ mark in LM file INFO: ngram_model_dmp.c(166): Will use memory-mapped I/O for LM file INFO: ngram_model_dmp.c(220): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_dmp.c(266): 3 = LM.unigrams(+trailer) read INFO: ngram_model_dmp.c(312): 2 = LM.bigrams(+trailer) read INFO: ngram_model_dmp.c(338): 1 = LM.trigrams read INFO: ngram_model_dmp.c(363): 2 = LM.prob2 entries read INFO: ngram_model_dmp.c(383): 3 = LM.bo_wt2 entries read INFO: ngram_model_dmp.c(403): 2 = LM.prob3 entries read INFO: ngram_model_dmp.c(431): 1 = LM.tseg_base entries read INFO: ngram_model_dmp.c(487): 3 = ascii word strings read App_Name(50827,0x103588000) malloc: *** error for object 0x1702910d0: Invalid pointer dequeued from free list *** set a breakpoint in malloc_error_break to debug (lldb)call stack:
Thread 12Queue : com.apple.root.default-qos (concurrent) #0 0x00000001948c7270 in __pthread_kill () #1 0x0000000194965170 in pthread_kill () #2 0x000000019483eb18 in abort () #3 0x00000001949023e4 in nanozone_error () #4 0x0000000194902550 in _nano_malloc_check_clear () #5 0x00000001949010dc in nano_calloc () #6 0x00000001948f595c in malloc_zone_calloc () #7 0x00000001948f58bc in calloc () #8 0x00000001004c7478 in __ckd_calloc_2d__ () #9 0x0000000100474c40 in ngram_search_init () #10 0x000000010046933c in ps_set_lm_file () #11 0x0000000100479f9c in ___lldb_unnamed_function183$$StampDrill () #12 0x0000000100461438 in ___lldb_unnamed_function78$$StampDrill () #13 0x0000000100461ac8 in ___lldb_unnamed_function82$$StampDrill () #14 0x000000010137cf94 in _dispatch_client_callout () #15 0x0000000101394848 in _dispatch_source_latch_and_call () #16 0x000000010137f1c0 in _dispatch_source_invoke () #17 0x000000010138a5d4 in _dispatch_root_queue_drain () #18 0x000000010138c248 in _dispatch_worker_thread3 () #19 0x000000019496122c in _pthread_wqthread ()anhtuParticipantSorry, I will create one again. I reseted the source code from git and forgot it.
anhtuParticipantHere is the contents of the files which you need. In this case , I tested from A-G. When came to letter C, it crashed.
lession_vocal_C_2.dic file
C S IYlession_vocal_C_2.arpa
############################################################################# ## Copyright (c) 1996, Carnegie Mellon University, Cambridge University, ## Ronald Rosenfeld and Philip Clarkson ## Version 3, Copyright (c) 2006, Carnegie Mellon University ## Contributors includes Wen Xu, Ananlada Chotimongkol, ## David Huggins-Daines, Arthur Chan and Alan Black ############################################################################# ============================================================================= =============== This file was produced by the CMU-Cambridge =============== =============== Statistical Language Modeling Toolkit =============== ============================================================================= This is a 3-gram language model, based on a vocabulary of 3 words, which begins "</s>", "<s>", "C"... This is a CLOSED-vocabulary model (OOVs eliminated from training data and are forbidden in test data) Witten Bell discounting was applied. This file is in the ARPA-standard format introduced by Doug Paul. p(wd3|wd1,wd2)= if(trigram exists) p_3(wd1,wd2,wd3) else if(bigram w1,w2 exists) bo_wt_2(w1,w2)*p(wd3|wd2) else p(wd3|w2) p(wd2|wd1)= if(bigram exists) p_2(wd1,wd2) else bo_wt_1(wd1)*p_1(wd2) All probs and back-off weights (bo_wt) are given in log10 form. Data formats: Beginning of data mark: \data\ ngram 1=nr # number of 1-grams ngram 2=nr # number of 2-grams ngram 3=nr # number of 3-grams \1-grams: p_1 wd_1 bo_wt_1 \2-grams: p_2 wd_1 wd_2 bo_wt_2 \3-grams: p_3 wd_1 wd_2 wd_3 end of data mark: \end\ \data\ ngram 1=3 ngram 2=2 ngram 3=1 \1-grams: -98.6990 </s> 0.0000 -98.6990 <s> -99.9990 0.0000 C -0.3010 \2-grams: -0.3010 <s> C 0.0000 -0.3010 C </s> -0.3010 \3-grams: -0.3010 <s> C </s> \end\the log console
2015-08-04 16:37:00.758 App_Name[50514:4263641] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-04 16:37:00.768 App_Name[50514:4263641] Starting dynamic language model generation 2015-08-04 16:37:00.892 App_Name[50514:4263641] Done creating language model with CMUCLMTK in 0.123174 seconds. 2015-08-04 16:37:00.900 App_Name[50514:4263641] I'm done running performDictionaryLookup and it took 0.002335 seconds 2015-08-04 16:37:00.908 App_Name[50514:4263641] I'm done running dynamic language model generation and it took 0.148800 seconds 2015-08-04 16:37:00.908 App_Name[50514:4263641] Valid setSecondsOfSilence value of 0.200000 will be used. 2015-08-04 16:37:01.017 App_Name[50514:4264050] there is a request to change to the language model file /var/mobile/Containers/Data/Application/A9D01313-E149-4F27-9067-EB2DA15AB639/Library/Caches/lession_vocal_B_1.DMP 2015-08-04 16:37:01.017 App_Name[50514:4264050] The language model ID is 1438681021 2015-08-04 16:37:01.032 App_Name[50514:4264050] Success loading the specified dictionary file /var/mobile/Containers/Data/Application/A9D01313-E149-4F27-9067-EB2DA15AB639/Library/Caches/lession_vocal_B_1.dic. 2015-08-04 16:37:01.033 App_Name[50514:4264050] Success loading the specified language model file /var/mobile/Containers/Data/Application/A9D01313-E149-4F27-9067-EB2DA15AB639/Library/Caches/lession_vocal_B_1.DMP. 2015-08-04 16:37:01.033 App_Name[50514:4263641] Pocketsphinx is now using the following language model: /var/mobile/Containers/Data/Application/A9D01313-E149-4F27-9067-EB2DA15AB639/Library/Caches/lession_vocal_B_1.DMP and the following dictionary: /var/mobile/Containers/Data/Application/A9D01313-E149-4F27-9067-EB2DA15AB639/Library/Caches/lession_vocal_B_1.dic 2015-08-04 16:37:01.039 App_Name[50514:4264050] Changed language model. Project has these words or phrases in its dictionary: B 2015-08-04 16:37:01.392 App_Name[50514:4264050] Speech detected... 2015-08-04 16:37:01.393 App_Name[50514:4264050] Pocketsphinx heard "" with a score of (-2680) and an utterance ID of 3. 2015-08-04 16:37:01.394 App_Name[50514:4264050] Hypothesis was null so we aren't returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController's property returnNullHypotheses to TRUE before starting OEPocketsphinxController. 2015-08-04 16:37:01.544 App_Name[50514:4264050] Pocketsphinx heard "B" with a score of (-5403) and an utterance ID of 4. 2015-08-04 16:37:01.585 App_Name[50514:4263641] rapidEarsDidReceiveFinishedSpeechHypothesis: B with score: -5403 2015-08-04 16:37:01.775 App_Name[50514:4263763] End of speech detected... 2015-08-04 16:37:01.779 App_Name[50514:4263641] pocketsphinxDidDetectFinishedSpeech 2015-08-04 16:37:01.785 App_Name[50514:4263763] Pocketsphinx heard "B" with a score of (-8131) and an utterance ID of 5. 2015-08-04 16:37:01.792 App_Name[50514:4263641] rapidEarsDidReceiveFinishedSpeechHypothesis: B with score: -8131 2015-08-04 16:37:03.404 App_Name[50514:4263641] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-04 16:37:03.416 App_Name[50514:4263641] Starting dynamic language model generation 2015-08-04 16:37:03.517 App_Name[50514:4263641] Done creating language model with CMUCLMTK in 0.100489 seconds. 2015-08-04 16:37:03.528 App_Name[50514:4263641] I'm done running performDictionaryLookup and it took 0.004014 seconds 2015-08-04 16:37:03.536 App_Name[50514:4263641] I'm done running dynamic language model generation and it took 0.131257 seconds 2015-08-04 16:37:03.536 App_Name[50514:4263641] Valid setSecondsOfSilence value of 0.200000 will be used. 2015-08-04 16:37:03.567 App_Name[50514:4264074] there is a request to change to the language model file /var/mobile/Containers/Data/Application/A9D01313-E149-4F27-9067-EB2DA15AB639/Library/Caches/lession_vocal_C_2.DMP 2015-08-04 16:37:03.569 App_Name[50514:4264074] The language model ID is 1438681023 App_Name(50514,0x104f10000) malloc: *** error for object 0x900000008: pointer being freed was not allocated *** set a breakpoint in malloc_error_break to debugcall stack
Thread 16Queue : com.apple.root.default-qos (concurent) #0 0x00000001948c7270 in __pthread_kill () #1 0x0000000194965170 in pthread_kill () #2 0x000000019483eb18 in abort () #3 0x00000001948f42fc in free () #4 0x0000000100473054 in ngram_model_set_map_words () #5 0x0000000100476598 in ___lldb_unnamed_function156$$App_Name () #6 0x00000001004693e4 in ps_load_dict () #7 0x0000000100479c10 in ___lldb_unnamed_function183$$App_Name () #8 0x00000001004611c8 in ___lldb_unnamed_function78$$App_Name () #9 0x0000000100461858 in ___lldb_unnamed_function82$$App_Name () #10 0x0000000101388f94 in _dispatch_client_callout () #11 0x00000001013a0848 in _dispatch_source_latch_and_call () #12 0x000000010138b1c0 in _dispatch_source_invoke () #13 0x00000001013965d4 in _dispatch_root_queue_drain () #14 0x0000000101398248 in _dispatch_worker_thread3 () #15 0x000000019496122c in _pthread_wqthread ()P.S: when I use REJECTO (demo version), this problem doesn’t appear. Here is the code I use:
error = [_languageModelGenerator generateRejectingLanguageModelFromArray:arrWords withFilesNamed:name withOptionalExclusions:[GlobalData sharedInstance].optionalExclusion usingVowelsOnly:[GlobalData sharedInstance].usingVowelsOnly withWeight:[NSNumber numberWithFloat: [GlobalData sharedInstance].weight_rejecto] forAcousticModelAtPath:[OEAcousticModel pathToModel:@"AcousticModelEnglish"]];anhtuParticipantThe contents of ‘lession_vocal_D_3.dic’ and ‘lession_vocal_D_3.DMP’ are the files which are created when the crash occurs in ‘D’ letter.
I will try to do experiments and post log + .DMP + .dic of a crash letter again.
anhtuParticipantHere is the contents in 2 files:
lession_vocal_D_3.dic
D D IYlession_vocal_D_3.DMP
Darpa Trigram LMr/var/mobile/Containers/Data/Application/2E00812C-8A05-4A6B-BFDC-475501A642DB/Library/Caches/lession_vocal_D_3.DMPˇˇˇˇBEGIN FILE FORMAT DESCRIPTION?Header string length (int32) and string (including trailing 0)OOriginal LM filename string-length (int32) and filename (including trailing 0)0(int32) version number (present iff value <= 0)G(int32) original LM file modification timestamp (iff version# present)O(int32) string-length and string (including trailing 0) (iff version# present)H... previous entry continued any number of times (iff version# present)C(int32) 0 (terminating sequence of strings) (iff version# present)S(int32) log_bg_seg_sz (present iff different from default value of LOG2_BG_SEG_SZ)"(int32) lm_t.ucount (must be > 0)(int32) lm_t.bcount(int32) lm_t.tcount,lm_t.ucount+1 unigrams (including sentinel)ulm_t.bcount+1 bigrams (including sentinel 64 bits (bg_t) each if version=-1/-2, 128 bits (bg32_t) each if version=-3}lm_t.tcount trigrams (present iff lm_t.tcount > 0 32 bits (tg_t) each if version=-1/-2, 64 bits (tg32_t) each if version=-3)(int32) lm_t.n_prob2(int32) lm_t.prob2[]4(int32) lm_t.n_bo_wt2 (present iff lm_t.tcount > 0)4(int32) lm_t.bo_wt2[] (present iff lm_t.tcount > 0)3(int32) lm_t.n_prob3 (present iff lm_t.tcount > 0)3(int32) lm_t.prob3[] (present iff lm_t.tcount > 0)B(int32) (lm_t.bcount+1)/BG_SEG_SZ+1 (present iff lm_t.tcount > 0)7(int32) lm_t.tseg_base[] (present iff lm_t.tcount > 0)D(int32) Sum(all word string-lengths, including trailing 0 for each)1All word strings (including trailing 0 for each)END FILE FORMAT DESCRIPTION!!!ˇˇˇˇ„e≈¬ˇˇˇˇ„e≈¬|ˇ«¬ˇˇˇˇÚöæˇˇˇˇ˝@.«˝@.«Ø%∂«ÚöæØ%∂«ÚöæØ%∂«Úöæ</s><s>DanhtuParticipantI’m using the default “AcousticModelEnglish.bundle” in OpenEars package.
I want the app can recognize letters A-Z.
The crash appears event if I keep “LanguageModelGeneratorLookupList.text” in the default or just keep A-Z.NSString *name = [NSString stringWithFormat:@"lession_vocal_%@_%d", [[QuestionManager sharedManager] getWordAtIndex:[index intValue]], [index intValue]]; NSError *error = nil; NSString * curLetter = [[QuestionManager sharedManager] getWordAtIndex:[index intValue]]; arrWords = @[curLetter]; if(![GlobalData sharedInstance].isRejectoON){ error = [_languageModelGenerator generateLanguageModelFromArray:arrWords withFilesNamed:name forAcousticModelAtPath:[OEAcousticModel pathToModel:@"AcousticModelEnglish"]]; }else{ error = [_languageModelGenerator generateRejectingLanguageModelFromArray:arrWords withFilesNamed:name withOptionalExclusions:[GlobalData sharedInstance].optionalExclusion usingVowelsOnly:[GlobalData sharedInstance].usingVowelsOnly withWeight:[NSNumber numberWithFloat: [GlobalData sharedInstance].weight_rejecto] forAcousticModelAtPath:[OEAcousticModel pathToModel:@"AcousticModelEnglish"]]; } lmPath = nil; dicPath = nil; if(error != noErr) { NSLog(@"Dynamic language generator reported error %@", [error description]); } else { dicPath = [_languageModelGenerator pathToSuccessfullyGeneratedDictionaryWithRequestedName:name]; lmPath = [_languageModelGenerator pathToSuccessfullyGeneratedLanguageModelWithRequestedName:name]; } [openEarsEventsObserver setDelegate:self]; //call before set properties [pocketsphinxController setActive:TRUE error:nil]; [pocketsphinxController setRapidEarsToVerbose:YES]; [pocketsphinxController setFinalizeHypothesis:NO]; [pocketsphinxController setReturnDuplicatePartials:false]; [pocketsphinxController setReturnNullHypotheses:false]; [pocketsphinxController setSecondsOfSilenceToDetect:0.2]; [OELogging startOpenEarsLogging]; if(!pocketsphinxController.isListening) { [pocketsphinxController startRealtimeListeningWithLanguageModelAtPath:lmPath dictionaryAtPath:dicPath acousticModelAtPath:[OEAcousticModel pathToModel:@"AcousticModelEnglish"]]; }else{ [pocketsphinxController changeLanguageModelToFile:lmPath withDictionary:dicPath]; if (pocketsphinxController.isSuspended) { [pocketsphinxController resumeRecognition]; } }The crash occurs rarely randomly and so weird. Because it doesn’t appear if I turn on Rejecto (using Rejecto)
The crash occurs on RapidEars 2.03 also.
anhtuParticipantand the error is “Thread 14: EXC_BAD_ACCESS (code=1,address=xxxx)”
anhtuParticipantSorry, here is the log (removed my logs):
2015-08-03 19:27:13.864 APP_NAME[49252:4174534] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-03 19:27:13.920 APP_NAME[49252:4174534] Starting dynamic language model generation 2015-08-03 19:27:14.062 APP_NAME[49252:4174534] Done creating language model with CMUCLMTK in 0.141510 seconds. 2015-08-03 19:27:14.064 APP_NAME[49252:4174534] I'm done running performDictionaryLookup and it took 0.000200 seconds 2015-08-03 19:27:14.071 APP_NAME[49252:4174534] I'm done running dynamic language model generation and it took 0.200374 seconds 2015-08-03 19:27:14.072 APP_NAME[49252:4174534] Starting OpenEars logging for OpenEars version 2.03 on 64-bit device (or build): iPad running iOS version: 8.300000 2015-08-03 19:27:14.080 APP_NAME[49252:4174534] cocos2d: surface size: 2048x1536 2015-08-03 19:27:15.083 APP_NAME[49252:4174534] User gave mic permission for this app. 2015-08-03 19:27:15.085 APP_NAME[49252:4174534] Valid setSecondsOfSilence value of 0.200000 will be used. 2015-08-03 19:27:15.087 APP_NAME[49252:4174708] Starting listening. 2015-08-03 19:27:15.088 APP_NAME[49252:4174708] about to set up audio session 2015-08-03 19:27:15.246 APP_NAME[49252:4174642] Audio route has changed for the following reason: 2015-08-03 19:27:15.249 APP_NAME[49252:4174642] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord 2015-08-03 19:27:15.256 APP_NAME[49252:4174642] This is not a case in which OpenEars notifies of a route change. At the close of this function, the new audio route is ---SpeakerMicrophoneBuiltIn---. The previous route before changing to this route was <AVAudioSessionRouteDescription: 0x170c118b0, inputs = (null); outputs = ( "<AVAudioSessionPortDescription: 0x170c11810, type = Speaker; name = Speaker; UID = Built-In Speaker; selectedDataSource = (null)>" )>. 2015-08-03 19:27:15.268 APP_NAME[49252:4174708] done starting audio unit INFO: cmd_ln.c(702): Parsing command line: \ -lm /var/mobile/Containers/Data/Application/662EA17C-590D-4F09-9312-520CD035DE4B/Library/Caches/lession_vocal_A_0.DMP \ -vad_prespeech 10 \ -vad_postspeech 20 \ -vad_threshold 2.000000 \ -remove_noise yes \ -remove_silence yes \ -bestpath yes \ -lw 6.500000 \ -dict /var/mobile/Containers/Data/Application/662EA17C-590D-4F09-9312-520CD035DE4B/Library/Caches/lession_vocal_A_0.dic \ -hmm /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle 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 -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 /var/mobile/Containers/Data/Application/662EA17C-590D-4F09-9312-520CD035DE4B/Library/Caches/lession_vocal_A_0.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 /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle -input_endian little little -jsgf -kdmaxbbi -1 -1 -kdmaxdepth 0 0 -kdtree -keyphrase -kws -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lextreedump 0 0 -lifter 0 0 -lm /var/mobile/Containers/Data/Application/662EA17C-590D-4F09-9312-520CD035DE4B/Library/Caches/lession_vocal_A_0.DMP -lmctl -lmname -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 10000 10000 -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 -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 legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -usewdphones no no -uw 1.0 1.000000e+00 -vad_postspeech 50 20 -vad_prespeech 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: cmd_ln.c(702): Parsing command line: \ -nfilt 25 \ -lowerf 130 \ -upperf 6800 \ -feat 1s_c_d_dd \ -svspec 0-12/13-25/26-38 \ -agc none \ -cmn current \ -varnorm no \ -transform dct \ -lifter 22 \ -cmninit 40 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 40 -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 22 -logspec no no -lowerf 133.33334 1.300000e+02 -ncep 13 13 -nfft 512 512 -nfilt 40 25 -remove_dc no no -remove_noise yes yes -remove_silence yes yes -round_filters yes yes -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 6.800000e+03 -vad_postspeech 50 20 -vad_prespeech 10 10 -vad_threshold 2.0 2.000000e+00 -varnorm no no -verbose no no -warp_params -warp_type inverse_linear inverse_linear -wlen 0.025625 2.562500e-02 INFO: acmod.c(252): Parsed model-specific feature parameters from /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/feat.params 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(171): Using subvector specification 0-12/13-25/26-38 INFO: mdef.c(518): Reading model definition: /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/mdef INFO: mdef.c(531): Found byte-order mark BMDF, assuming this is a binary mdef file INFO: bin_mdef.c(336): Reading binary model definition: /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/mdef INFO: bin_mdef.c(516): 46 CI-phone, 168344 CD-phone, 3 emitstate/phone, 138 CI-sen, 6138 Sen, 32881 Sen-Seq INFO: tmat.c(206): Reading HMM transition probability matrices: /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/transition_matrices INFO: acmod.c(124): Attempting to use SCHMM computation module INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/means INFO: ms_gauden.c(292): 1 codebook, 3 feature, size: INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/variances INFO: ms_gauden.c(292): 1 codebook, 3 feature, size: INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(294): 512x13 INFO: ms_gauden.c(354): 0 variance values floored INFO: s2_semi_mgau.c(904): Loading senones from dump file /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/sendump INFO: s2_semi_mgau.c(928): BEGIN FILE FORMAT DESCRIPTION INFO: s2_semi_mgau.c(991): Rows: 512, Columns: 6138 INFO: s2_semi_mgau.c(1023): Using memory-mapped I/O for senones INFO: s2_semi_mgau.c(1294): Maximum top-N: 4 Top-N beams: 0 0 0 INFO: dict.c(320): Allocating 4110 * 32 bytes (128 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/662EA17C-590D-4F09-9312-520CD035DE4B/Library/Caches/lession_vocal_A_0.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 1 words read INFO: dict.c(342): Reading filler dictionary: /private/var/mobile/Containers/Bundle/Application/204102C4-D4A7-4B27-ABC4-9072CA281718/APP_NAME.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(345): 9 words read INFO: dict2pid.c(396): Building PID tables for dictionary INFO: dict2pid.c(406): Allocating 46^3 * 2 bytes (190 KiB) for word-initial triphones INFO: dict2pid.c(132): Allocated 51152 bytes (49 KiB) for word-final triphones INFO: dict2pid.c(196): Allocated 51152 bytes (49 KiB) for single-phone word triphones INFO: ngram_model_arpa.c(79): No \data\ mark in LM file INFO: ngram_model_dmp.c(166): Will use memory-mapped I/O for LM file INFO: ngram_model_dmp.c(220): ngrams 1=3, 2=2, 3=1 INFO: ngram_model_dmp.c(266): 3 = LM.unigrams(+trailer) read INFO: ngram_model_dmp.c(312): 2 = LM.bigrams(+trailer) read INFO: ngram_model_dmp.c(338): 1 = LM.trigrams read INFO: ngram_model_dmp.c(363): 2 = LM.prob2 entries read INFO: ngram_model_dmp.c(383): 3 = LM.bo_wt2 entries read INFO: ngram_model_dmp.c(403): 2 = LM.prob3 entries read INFO: ngram_model_dmp.c(431): 1 = LM.tseg_base entries read INFO: ngram_model_dmp.c(487): 3 = ascii word strings read INFO: ngram_search_fwdtree.c(99): 0 unique initial diphones INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 11 single-phone words INFO: ngram_search_fwdtree.c(186): Creating search tree INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 11 single-phone words INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 128 ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has pronunciation in the dictionary INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 10 single-phone words INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25 2015-08-03 19:27:15.363 APP_NAME[49252:4174708] Restoring SmartCMN value of 55.322021 2015-08-03 19:27:15.363 APP_NAME[49252:4174708] Listening. 2015-08-03 19:27:15.364 APP_NAME[49252:4174708] Project has these words or phrases in its dictionary: A 2015-08-03 19:27:15.364 APP_NAME[49252:4174708] Recognition loop has started 2015-08-03 19:27:15.368 APP_NAME[49252:4174534] Pocketsphinx is now listening. 2015-08-03 19:27:20.707 APP_NAME[49252:4174708] Speech detected... 2015-08-03 19:27:20.708 APP_NAME[49252:4174708] Pocketsphinx heard "" with a score of (-1580) and an utterance ID of 0. 2015-08-03 19:27:20.802 APP_NAME[49252:4174708] Pocketsphinx heard "" with a score of (-2757) and an utterance ID of 1. 2015-08-03 19:27:20.897 APP_NAME[49252:4174708] Pocketsphinx heard "" with a score of (-4058) and an utterance ID of 2. 2015-08-03 19:27:21.056 APP_NAME[49252:4174708] Pocketsphinx heard "" with a score of (-6635) and an utterance ID of 3. 2015-08-03 19:27:21.169 APP_NAME[49252:4174708] End of speech detected... INFO: cmn_prior.c(131): cmn_prior_update: from < 55.32 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 > INFO: cmn_prior.c(149): cmn_prior_update: to < 49.58 16.76 -1.75 9.75 -9.41 9.58 1.37 2.40 -8.62 6.90 -3.80 -2.46 6.97 > INFO: ngram_search_fwdtree.c(1550): 483 words recognized (9/fr) INFO: ngram_search_fwdtree.c(1552): 1585 senones evaluated (29/fr) INFO: ngram_search_fwdtree.c(1556): 503 channels searched (9/fr), 0 1st, 503 last INFO: ngram_search_fwdtree.c(1559): 503 words for which last channels evaluated (9/fr) INFO: ngram_search_fwdtree.c(1561): 0 candidate words for entering last phone (0/fr) INFO: ngram_search_fwdtree.c(1564): fwdtree 1.15 CPU 2.137 xRT INFO: ngram_search_fwdtree.c(1567): fwdtree 5.64 wall 10.438 xRT INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 3 words INFO: ngram_search_fwdflat.c(938): 400 words recognized (7/fr) INFO: ngram_search_fwdflat.c(940): 1638 senones evaluated (30/fr) INFO: ngram_search_fwdflat.c(942): 519 channels searched (9/fr) INFO: ngram_search_fwdflat.c(944): 519 words searched (9/fr) INFO: ngram_search_fwdflat.c(947): 121 word transitions (2/fr) INFO: ngram_search_fwdflat.c(950): fwdflat 0.01 CPU 0.022 xRT INFO: ngram_search_fwdflat.c(953): fwdflat 0.01 wall 0.021 xRT INFO: ngram_search.c(1215): </s> not found in last frame, using A.52 instead INFO: ngram_search.c(1268): lattice start node <s>.0 end node A.49 INFO: ngram_search.c(1294): Eliminated 1 nodes before end node INFO: ngram_search.c(1399): Lattice has 99 nodes, 600 links 2015-08-03 19:27:21.185 APP_NAME[49252:4174534] pocketsphinxDidDetectFinishedSpeech (lldb)and call stack:
Thread 14Queue : com.apple.root.default-qos (concurrent) #0 0x00000001004ec83c in logmath_add () #1 0x00000001004c9128 in ps_lattice_bestpath () #2 0x00000001004b556c in ___lldb_unnamed_function157$$StampDrill () #3 0x000000010049ef3c in ps_get_hyp_vnnetvisstampdrill () #4 0x000000010049e69c in ___lldb_unnamed_function74$$StampDrill () #5 0x00000001004a04e8 in ___lldb_unnamed_function78$$StampDrill () #6 0x00000001004a0758 in ___lldb_unnamed_function82$$StampDrill () #7 0x00000001013d4f94 in _dispatch_client_callout () #8 0x00000001013ec848 in _dispatch_source_latch_and_call () #9 0x00000001013d71c0 in _dispatch_source_invoke () #10 0x00000001013e25d4 in _dispatch_root_queue_drain () #11 0x00000001013e4248 in _dispatch_worker_thread3 () #12 0x000000019496122c in _pthread_wqthread ()Thank you very much
-
AuthorPosts
Viewing 11 posts - 1 through 11 (of 11 total)