- This topic has 12 replies, 3 voices, and was last updated 8 years, 5 months ago by Halle Winkler.
-
AuthorPosts
-
October 18, 2015 at 2:49 am #1027058SaliencyParticipant
Hello,
During an ongoing listening session I am trying to switch to another JSGF grammar using:
@property (strong) OELanguageModelGenerator *lmGenerator; ... lmPath = [self.lmGenerator pathToSuccessfullyGeneratedGrammarWithRequestedName:name]; dicPath = [self.lmGenerator pathToSuccessfullyGeneratedDictionaryWithRequestedName:name]; [[OEPocketsphinxController sharedInstance] changeLanguageModelToFile:lmPath withDictionary:dicPath];
However, when I do this, I get an EXC_BAD_ACCESS as per the logs below.
Is there a solution to this problem?
Thank you,
Saliency[spoiler]
2015-10-17 17:39:07.218 Converse2[342:22257] Did load 2015-10-17 17:39:07.220 Converse2[342:22257] Starting OpenEars logging for OpenEars version 2.041 on 64-bit device (or build): iPhone running iOS version: 9.000000 2015-10-17 17:44:04.698 Converse2[342:23162] Creating shared instance of OEPocketsphinxController 2015-10-17 17:44:04.715 Converse2[342:23162] User gave mic permission for this app. 2015-10-17 17:44:04.821 Converse2[342:22257] The word was not found in the dictionary /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.app/AcousticModelEnglish.bundle/LanguageModelGeneratorLookupList.text/LanguageModelGeneratorLookupList.text. 2015-10-17 17:44:04.821 Converse2[342:22257] Now using the fallback method to look up the word 2015-10-17 17:44:04.822 Converse2[342:22257] If this is happening more frequently than you would expect, the most likely cause for it is since you are using the English phonetic lookup dictionary is that your words are not in English or aren't dictionary words. 2015-10-17 17:44:04.822 Converse2[342:22257] Using convertGraphemes for the word or phrase which doesn't appear in the dictionary 2015-10-17 17:44:04.863 Converse2[342:22257] I'm done running performDictionaryLookup and it took 0.090061 seconds 2015-10-17 17:44:04.886 Converse2[342:22257] Attempting to start listening session from startListeningWithLanguageModelAtPath: 2015-10-17 17:44:04.886 Converse2[342:22257] User gave mic permission for this app. 2015-10-17 17:44:04.887 Converse2[342:22257] Valid setSecondsOfSilence value of 0.800000 will be used. 2015-10-17 17:44:04.887 Converse2[342:22257] Successfully started listening session from startListeningWithLanguageModelAtPath: 2015-10-17 17:44:04.887 Converse2[342:23170] Starting listening. 2015-10-17 17:44:04.887 Converse2[342:23170] about to set up audio session 2015-10-17 17:44:05.106 Converse2[342:23170] Creating audio session with default settings. 2015-10-17 17:44:05.111 Converse2[342:22337] Audio route has changed for the following reason: 2015-10-17 17:44:05.115 Converse2[342:22337] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord 2015-10-17 17:44:05.136 Converse2[342:22337] This is not a case in which OpenEars notifies of a route change. At the close of this function, the new audio route is ---HeadphonesMicrophoneBuiltIn---. The previous route before changing to this route was <AVAudioSessionRouteDescription: 0x135d3daa0, inputs = ( "<AVAudioSessionPortDescription: 0x135d3d530, type = MicrophoneBuiltIn; name = iPhone Microphone; UID = Built-In Microphone; selectedDataSource = Front>" ); outputs = ( "<AVAudioSessionPortDescription: 0x135d3e140, type = Headphones; name = Headphones; UID = Wired Headphones; selectedDataSource = (null)>" )>. 2015-10-17 17:44:05.311 Converse2[342:23170] done starting audio unit INFO: cmd_ln.c(703): Parsing command line: \ -jsgf /var/mobile/Containers/Data/Application/30E675A2-1C1F-46B2-AC86-FAE4A5D23747/Library/Caches/mathModel2.gram \ -vad_prespeech 10 \ -vad_postspeech 80 \ -vad_threshold 3.500000 \ -remove_noise yes \ -remove_silence yes \ -bestpath yes \ -lw 1.000000 \ -dict /var/mobile/Containers/Data/Application/30E675A2-1C1F-46B2-AC86-FAE4A5D23747/Library/Caches/mathModel2.dic \ -hmm /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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 -ceplen 13 13 -cmn current current -cmninit 8.0 8.0 -compallsen no no -debug 0 -dict /var/mobile/Containers/Data/Application/30E675A2-1C1F-46B2-AC86-FAE4A5D23747/Library/Caches/mathModel2.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 /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.app/AcousticModelEnglish.bundle -input_endian little little -jsgf /var/mobile/Containers/Data/Application/30E675A2-1C1F-46B2-AC86-FAE4A5D23747/Library/Caches/mathModel2.gram -keyphrase -kws -kws_delay 10 10 -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lifter 0 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 1.000000e+00 -maxhmmpf 30000 30000 -maxwpf -1 -1 -mdef -mean -mfclogdir -min_endfr 0 0 -mixw -mixwfloor 0.0000001 1.000000e-07 -mllr -mmap yes yes -ncep 13 13 -nfft 512 512 -nfilt 40 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-10 1.000000e-10 -pl_pip 1.0 1.000000e+00 -pl_weight 3.0 3.000000e+00 -pl_window 5 5 -rawlogdir -remove_dc no no -remove_noise yes yes -remove_silence yes yes -round_filters yes yes -samprate 16000 1.600000e+04 -seed -1 -1 -sendump -senlogdir -senmgau -silprob 0.005 5.000000e-03 -smoothspec no no -svspec -tmat -tmatfloor 0.0001 1.000000e-04 -topn 4 4 -topn_beam 0 0 -toprule -transform legacy legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -uw 1.0 1.000000e+00 -vad_postspeech 50 80 -vad_prespeech 20 10 -vad_startspeech 10 10 -vad_threshold 2.0 3.500000e+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(703): 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 80 -vad_prespeech 20 10 -vad_startspeech 10 10 -vad_threshold 2.0 3.500000e+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 /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.app/AcousticModelEnglish.bundle/transition_matrices INFO: acmod.c(124): Attempting to use PTM computation module INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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: ptm_mgau.c(805): Number of codebooks doesn't match number of ciphones, doesn't look like PTM: 1 != 46 INFO: acmod.c(126): Attempting to use semi-continuous computation module INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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 /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.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: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0 INFO: dict.c(320): Allocating 4145 * 32 bytes (129 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/30E675A2-1C1F-46B2-AC86-FAE4A5D23747/Library/Caches/mathModel2.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 39 words read INFO: dict.c(358): Reading filler dictionary: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(361): 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: jsgf.c(691): Defined rule: <mathModel2.g00000> INFO: jsgf.c(691): Defined rule: <mathModel2.rule_0> INFO: jsgf.c(691): Defined rule: <mathModel2.g00002> INFO: jsgf.c(691): Defined rule: <mathModel2.rule_1> INFO: jsgf.c(691): Defined rule: <mathModel2.g00004> INFO: jsgf.c(691): Defined rule: <mathModel2.g00005> INFO: jsgf.c(691): Defined rule: <mathModel2.rule_2> INFO: jsgf.c(691): Defined rule: <mathModel2.g00007> INFO: jsgf.c(691): Defined rule: PUBLIC <mathModel2.rule_3> INFO: jsgf.c(359): Right recursion <mathModel2.g00005> 13 => 4 INFO: fsg_model.c(215): Computing transitive closure for null transitions INFO: fsg_model.c(277): 1 null transitions added INFO: fsg_search.c(227): FSG(beam: -1080, pbeam: -1080, wbeam: -634; wip: -5, pip: 0) INFO: fsg_model.c(428): Adding silence transitions for <sil> to FSG INFO: fsg_model.c(448): Added 14 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for <sil> to FSG INFO: fsg_model.c(448): Added 14 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [BREATH] to FSG INFO: fsg_model.c(448): Added 14 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [COUGH] to FSG INFO: fsg_model.c(448): Added 14 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [NOISE] to FSG INFO: fsg_model.c(448): Added 14 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [SMACK] to FSG INFO: fsg_model.c(448): Added 14 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [UH] to FSG INFO: fsg_model.c(448): Added 14 silence word transitions INFO: fsg_search.c(173): Added 9 alternate word transitions INFO: fsg_lextree.c(110): Allocated 1316 bytes (1 KiB) for left and right context phones INFO: fsg_lextree.c(256): 497 HMM nodes in lextree (411 leaves) INFO: fsg_lextree.c(259): Allocated 71568 bytes (69 KiB) for all lextree nodes INFO: fsg_lextree.c(262): Allocated 59184 bytes (57 KiB) for lextree leafnodes 2015-10-17 17:44:05.391 Converse2[342:23170] Restoring SmartCMN value of 46.493896 2015-10-17 17:44:05.392 Converse2[342:23170] Listening. 2015-10-17 17:44:05.393 Converse2[342:23170] Project has these words or phrases in its dictionary: A A(2) ALL CALCULATE DONE EIGHT FIVE FOUR GRAMMAR HEY IS LOT LOT(2) NINE NORMAL OH ONE ONE(2) PLUS POINT SEVEN SIX SWITCH THANK THANKS THREE TIMES TO TO(2) TO(3) ...and 10 more. 2015-10-17 17:44:05.393 Converse2[342:23170] Recognition loop has started 2015-10-17 17:44:05.394 Converse2[342:22257] Pocketsphinx is now listening. 2015-10-17 17:44:09.182 Converse2[342:23170] Speech detected... 2015-10-17 17:44:09.184 Converse2[342:22257] Pocketsphinx has detected speech. 2015-10-17 17:44:11.084 Converse2[342:23170] End of speech detected... 2015-10-17 17:44:11.085 Converse2[342:22257] Pocketsphinx has detected a period of silence, concluding an utterance. INFO: cmn_prior.c(131): cmn_prior_update: from < 46.49 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 < 47.78 4.36 -1.05 6.52 -1.17 -2.24 3.14 -4.49 0.33 4.60 -0.21 -8.18 0.54 > INFO: fsg_search.c(843): 196 frames, 11134 HMMs (56/fr), 25803 senones (131/fr), 2276 history entries (11/fr) 2015-10-17 17:44:11.087 Converse2[342:23170] Pocketsphinx heard "HEY SWITCH TO NORMAL GRAMMAR" with a score of (0) and an utterance ID of 0. 2015-10-17 17:44:11.169 Converse2[342:22257] The word was not found in the dictionary /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.app/AcousticModelEnglish.bundle/LanguageModelGeneratorLookupList.text/LanguageModelGeneratorLookupList.text. 2015-10-17 17:44:11.169 Converse2[342:22257] Now using the fallback method to look up the word 2015-10-17 17:44:11.169 Converse2[342:22257] If this is happening more frequently than you would expect, the most likely cause for it is since you are using the English phonetic lookup dictionary is that your words are not in English or aren't dictionary words. 2015-10-17 17:44:11.170 Converse2[342:22257] Using convertGraphemes for the word or phrase which doesn't appear in the dictionary 2015-10-17 17:44:11.206 Converse2[342:22257] I'm done running performDictionaryLookup and it took 0.086398 seconds INFO: cmn_prior.c(131): cmn_prior_update: from < 47.78 4.36 -1.05 6.52 -1.17 -2.24 3.14 -4.49 0.33 4.60 -0.21 -8.18 0.54 > INFO: cmn_prior.c(149): cmn_prior_update: to < 47.78 4.36 -1.05 6.52 -1.17 -2.24 3.14 -4.49 0.33 4.60 -0.21 -8.18 0.54 > INFO: fsg_search.c(843): 0 frames, 0 HMMs (0/fr), 0 senones (0/fr), 1 history entries (0/fr) 2015-10-17 17:44:11.311 Converse2[342:23170] there is a request to change to the grammar file /var/mobile/Containers/Data/Application/30E675A2-1C1F-46B2-AC86-FAE4A5D23747/Library/Caches/normalModel2.gram 2015-10-17 17:44:11.311 Converse2[342:23170] The grammar ID is 1445129051 INFO: cmd_ln.c(703): 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 -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 -keyphrase -kws -kws_delay 10 10 -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lifter 0 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 30000 30000 -maxwpf -1 -1 -mdef -mean -mfclogdir -min_endfr 0 0 -mixw -mixwfloor 0.0000001 1.000000e-07 -mllr -mmap yes yes -ncep 13 13 -nfft 512 512 -nfilt 40 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-10 1.000000e-10 -pl_pip 1.0 1.000000e+00 -pl_weight 3.0 3.000000e+00 -pl_window 5 5 -rawlogdir -remove_dc no no -remove_noise yes yes -remove_silence yes yes -round_filters yes yes -samprate 16000 1.600000e+04 -seed -1 -1 -sendump -senlogdir -senmgau -silprob 0.005 5.000000e-03 -smoothspec no no -svspec -tmat -tmatfloor 0.0001 1.000000e-04 -topn 4 4 -topn_beam 0 0 -toprule -transform legacy legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -uw 1.0 1.000000e+00 -vad_postspeech 50 50 -vad_prespeech 20 20 -vad_startspeech 10 10 -vad_threshold 2.0 2.000000e+00 -var -varfloor 0.0001 1.000000e-04 -varnorm no no -verbose no no -warp_params -warp_type inverse_linear inverse_linear -wbeam 7e-29 7.000000e-29 -wip 0.65 6.500000e-01 -wlen 0.025625 2.562500e-02 INFO: dict.c(320): Allocating 4125 * 32 bytes (128 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/30E675A2-1C1F-46B2-AC86-FAE4A5D23747/Library/Caches/normalModel2.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 19 words read INFO: dict.c(358): Reading filler dictionary: /var/mobile/Containers/Bundle/Application/9F5F0885-A8B2-48DE-991B-5C7B4A7A95E7/Converse2.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(361): 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: fsg_lextree.c(110): Allocated 1316 bytes (1 KiB) for left and right context phones [/spoiler] (lldb) bt * thread #11: tid = 0x5a82, 0x000000010007fb60 Converse2
fsg_lextree_init + 516, queue = ‘com.apple.root.default-qos’, stop reason = EXC_BAD_ACCESS (code=1, address=0x0)
* frame #0: 0x000000010007fb60 Converse2`fsg_lextree_init + 516
frame #1: 0x0000000100051f08 Converse2`fsg_search_reinit + 92
frame #2: 0x000000010002acec Converse2`ps_load_dict + 364
frame #3: 0x000000010003a80c Converse2`___lldb_unnamed_function58$$Converse2 + 428
frame #4: 0x0000000100039618 Converse2`___lldb_unnamed_function49$$Converse2 + 128
frame #5: 0x0000000100039214 Converse2`___lldb_unnamed_function42$$Converse2 + 348
frame #6: 0x00000001003b5d30 libdispatch.dylib`_dispatch_client_callout + 16
frame #7: 0x00000001003ce00c libdispatch.dylib`_dispatch_source_latch_and_call + 2848
frame #8: 0x00000001003b82d4 libdispatch.dylib`_dispatch_source_invoke + 808
frame #9: 0x00000001003c4908 libdispatch.dylib`_dispatch_root_queue_drain + 760
frame #10: 0x00000001003c4600 libdispatch.dylib`_dispatch_worker_thread3 + 132
frame #11: 0x000000019a839478 libsystem_pthread.dylib`_pthread_wqthread + 1092
(lldb)
`October 18, 2015 at 10:11 am #1027061Halle WinklerPolitepixWelcome,
Hmm, I’ve never seen that before but what jumps out at me is that it looks like the grammar is being generated after the command to switch grammars – do you have the same issue if you first create the grammar and then switch to it?
October 18, 2015 at 1:38 pm #1027062SaliencyParticipantThank you.
The same issue still happens if I create both grammars upfront… anything else I can try?
I really like the grammar syntax, by the way!
[spoiler]2015-10-18 04:34:35.825 Converse2[598:112503] Starting OpenEars logging for OpenEars version 2.041 on 64-bit device (or build): iPhone running iOS version: 9.000000 2015-10-18 04:34:37.058 Converse2[598:112522] Creating shared instance of OEPocketsphinxController 2015-10-18 04:34:37.078 Converse2[598:112522] User gave mic permission for this app. 2015-10-18 04:34:37.242 Converse2[598:112522] The word was not found in the dictionary /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.app/AcousticModelEnglish.bundle/LanguageModelGeneratorLookupList.text/LanguageModelGeneratorLookupList.text. 2015-10-18 04:34:37.244 Converse2[598:112522] Now using the fallback method to look up the word 2015-10-18 04:34:37.244 Converse2[598:112522] If this is happening more frequently than you would expect, the most likely cause for it is since you are using the English phonetic lookup dictionary is that your words are not in English or aren't dictionary words. 2015-10-18 04:34:37.244 Converse2[598:112522] Using convertGraphemes for the word or phrase which doesn't appear in the dictionary 2015-10-18 04:34:37.283 Converse2[598:112522] I'm done running performDictionaryLookup and it took 0.156046 seconds 2015-10-18 04:34:37.341 Converse2[598:112522] ----- Generated language model name mathModel2 at lmPath /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/mathModel2.gram and dicPath /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/mathModel2.dic 2015-10-18 04:34:37.394 Converse2[598:112522] The word was not found in the dictionary /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.app/AcousticModelEnglish.bundle/LanguageModelGeneratorLookupList.text/LanguageModelGeneratorLookupList.text. 2015-10-18 04:34:37.394 Converse2[598:112522] Now using the fallback method to look up the word 2015-10-18 04:34:37.394 Converse2[598:112522] If this is happening more frequently than you would expect, the most likely cause for it is since you are using the English phonetic lookup dictionary is that your words are not in English or aren't dictionary words. 2015-10-18 04:34:37.394 Converse2[598:112522] Using convertGraphemes for the word or phrase which doesn't appear in the dictionary 2015-10-18 04:34:37.431 Converse2[598:112522] I'm done running performDictionaryLookup and it took 0.073644 seconds 2015-10-18 04:34:37.451 Converse2[598:112522] ----- Generated language model name normalModel2 at lmPath /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/normalModel2.gram and dicPath /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/normalModel2.dic 2015-10-18 04:34:37.451 Converse2[598:112522] Attempting to start listening session from startListeningWithLanguageModelAtPath: 2015-10-18 04:34:37.452 Converse2[598:112522] User gave mic permission for this app. 2015-10-18 04:34:37.453 Converse2[598:112522] Valid setSecondsOfSilence value of 0.800000 will be used. 2015-10-18 04:34:37.453 Converse2[598:112522] Successfully started listening session from startListeningWithLanguageModelAtPath: 2015-10-18 04:34:37.454 Converse2[598:112525] Starting listening. 2015-10-18 04:34:37.454 Converse2[598:112525] about to set up audio session 2015-10-18 04:34:37.455 Converse2[598:112525] Creating audio session with default settings. 2015-10-18 04:34:37.887 Converse2[598:112548] Audio route has changed for the following reason: 2015-10-18 04:34:37.896 Converse2[598:112548] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord 2015-10-18 04:34:38.076 Converse2[598:112525] done starting audio unit INFO: cmd_ln.c(703): Parsing command line: \ -jsgf /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/normalModel2.gram \ -vad_prespeech 10 \ -vad_postspeech 80 \ -vad_threshold 3.500000 \ -remove_noise yes \ -remove_silence yes \ -bestpath yes \ -lw 1.000000 \ -dict /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/normalModel2.dic \ -hmm /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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 -ceplen 13 13 -cmn current current -cmninit 8.0 8.0 -compallsen no no -debug 0 -dict /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/normalModel2.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 /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.app/AcousticModelEnglish.bundle -input_endian little little -jsgf /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/normalModel2.gram -keyphrase -kws -kws_delay 10 10 -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lifter 0 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 1.000000e+00 -maxhmmpf 30000 30000 -maxwpf -1 -1 -mdef -mean -mfclogdir -min_endfr 0 0 -mixw -mixwfloor 0.0000001 1.000000e-07 -mllr -mmap yes yes -ncep 13 13 -nfft 512 512 -nfilt 40 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-10 1.000000e-10 -pl_pip 1.0 1.000000e+00 -pl_weight 3.0 3.000000e+00 -pl_window 5 5 -rawlogdir -remove_dc no no -remove_noise yes yes -remove_silence yes yes -round_filters yes yes -samprate 16000 1.600000e+04 -seed -1 -1 -sendump -senlogdir -senmgau -silprob 0.005 5.000000e-03 -smoothspec no no -svspec -tmat -tmatfloor 0.0001 1.000000e-04 -topn 4 4 -topn_beam 0 0 -toprule -transform legacy legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -uw 1.0 1.000000e+00 -vad_postspeech 50 80 -vad_prespeech 20 10 -vad_startspeech 10 10 -vad_threshold 2.0 3.500000e+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(703): 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 80 -vad_prespeech 20 10 -vad_startspeech 10 10 -vad_threshold 2.0 3.500000e+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 /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.app/AcousticModelEnglish.bundle/feat.params 2015-10-18 04:34:38.084 Converse2[598:112548] 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: 0x1255516c0, inputs = ( "<AVAudioSessionPortDescription: 0x12553be40, type = MicrophoneBuiltIn; name = iPhone Microphone; UID = Built-In Microphone; selectedDataSource = Front>" ); outputs = ( "<AVAudioSessionPortDescription: 0x12555a2a0, type = Speaker; name = Speaker; UID = Speaker; selectedDataSource = (null)>" )>. 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: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.app/AcousticModelEnglish.bundle/transition_matrices INFO: acmod.c(124): Attempting to use PTM computation module INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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: ptm_mgau.c(805): Number of codebooks doesn't match number of ciphones, doesn't look like PTM: 1 != 46 INFO: acmod.c(126): Attempting to use semi-continuous computation module INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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 /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.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: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0 INFO: dict.c(320): Allocating 4125 * 32 bytes (128 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/normalModel2.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 19 words read INFO: dict.c(358): Reading filler dictionary: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(361): 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: jsgf.c(691): Defined rule: <normalModel2.g00000> INFO: jsgf.c(691): Defined rule: <normalModel2.rule_0> INFO: jsgf.c(691): Defined rule: <normalModel2.g00002> INFO: jsgf.c(691): Defined rule: <normalModel2.rule_1> INFO: jsgf.c(691): Defined rule: <normalModel2.g00004> INFO: jsgf.c(691): Defined rule: PUBLIC <normalModel2.rule_2> INFO: fsg_model.c(215): Computing transitive closure for null transitions INFO: fsg_model.c(277): 0 null transitions added INFO: fsg_search.c(227): FSG(beam: -1080, pbeam: -1080, wbeam: -634; wip: -5, pip: 0) INFO: fsg_model.c(428): Adding silence transitions for <sil> to FSG INFO: fsg_model.c(448): Added 15 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for <sil> to FSG INFO: fsg_model.c(448): Added 15 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [BREATH] to FSG INFO: fsg_model.c(448): Added 15 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [COUGH] to FSG INFO: fsg_model.c(448): Added 15 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [NOISE] to FSG INFO: fsg_model.c(448): Added 15 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [SMACK] to FSG INFO: fsg_model.c(448): Added 15 silence word transitions INFO: fsg_model.c(428): Adding silence transitions for [UH] to FSG INFO: fsg_model.c(448): Added 15 silence word transitions INFO: fsg_search.c(173): Added 5 alternate word transitions INFO: fsg_lextree.c(110): Allocated 1410 bytes (1 KiB) for left and right context phones INFO: fsg_lextree.c(256): 198 HMM nodes in lextree (137 leaves) INFO: fsg_lextree.c(259): Allocated 28512 bytes (27 KiB) for all lextree nodes INFO: fsg_lextree.c(262): Allocated 19728 bytes (19 KiB) for lextree leafnodes 2015-10-18 04:34:38.136 Converse2[598:112525] There was no previous CMN value in the plist so we are using the fresh CMN value 42.000000. 2015-10-18 04:34:38.137 Converse2[598:112525] Listening. 2015-10-18 04:34:38.137 Converse2[598:112503] Pocketsphinx is now listening. 2015-10-18 04:34:38.137 Converse2[598:112525] Project has these words or phrases in its dictionary: CALCULATOR DO ENABLE ENABLE(2) GRAMMAR HEY IS IT LET'S MATH MODE SOME SWITCH TIME TO TO(2) TO(3) WHAT WHAT(2) 2015-10-18 04:34:38.138 Converse2[598:112525] Recognition loop has started 2015-10-18 04:34:40.701 Converse2[598:112522] Speech detected... 2015-10-18 04:34:40.702 Converse2[598:112503] Pocketsphinx has detected speech. 2015-10-18 04:34:42.634 Converse2[598:112522] End of speech detected... 2015-10-18 04:34:42.635 Converse2[598:112503] Pocketsphinx has detected a period of silence, concluding an utterance. INFO: cmn_prior.c(131): cmn_prior_update: from < 42.00 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 < 47.59 2.63 1.52 5.51 -4.49 10.41 -0.17 5.00 1.14 3.83 3.19 -16.00 -17.33 > INFO: fsg_search.c(843): 190 frames, 4477 HMMs (23/fr), 11469 senones (60/fr), 647 history entries (3/fr) 2015-10-18 04:34:42.637 Converse2[598:112522] Pocketsphinx heard "HEY SWITCH TO MATH GRAMMAR" with a score of (0) and an utterance ID of 0. INFO: cmn_prior.c(131): cmn_prior_update: from < 47.59 2.63 1.52 5.51 -4.49 10.41 -0.17 5.00 1.14 3.83 3.19 -16.00 -17.33 > INFO: cmn_prior.c(149): cmn_prior_update: to < 47.59 2.63 1.52 5.51 -4.49 10.41 -0.17 5.00 1.14 3.83 3.19 -16.00 -17.33 > INFO: fsg_search.c(843): 0 frames, 0 HMMs (0/fr), 0 senones (0/fr), 1 history entries (0/fr) 2015-10-18 04:34:42.768 Converse2[598:112522] there is a request to change to the grammar file /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/mathModel2.gram 2015-10-18 04:34:42.769 Converse2[598:112522] The grammar ID is 1445168082 INFO: cmd_ln.c(703): 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 -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 -keyphrase -kws -kws_delay 10 10 -kws_plp 1e-1 1.000000e-01 -kws_threshold 1 1.000000e+00 -latsize 5000 5000 -lda -ldadim 0 0 -lifter 0 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 30000 30000 -maxwpf -1 -1 -mdef -mean -mfclogdir -min_endfr 0 0 -mixw -mixwfloor 0.0000001 1.000000e-07 -mllr -mmap yes yes -ncep 13 13 -nfft 512 512 -nfilt 40 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-10 1.000000e-10 -pl_pip 1.0 1.000000e+00 -pl_weight 3.0 3.000000e+00 -pl_window 5 5 -rawlogdir -remove_dc no no -remove_noise yes yes -remove_silence yes yes -round_filters yes yes -samprate 16000 1.600000e+04 -seed -1 -1 -sendump -senlogdir -senmgau -silprob 0.005 5.000000e-03 -smoothspec no no -svspec -tmat -tmatfloor 0.0001 1.000000e-04 -topn 4 4 -topn_beam 0 0 -toprule -transform legacy legacy -unit_area yes yes -upperf 6855.4976 6.855498e+03 -uw 1.0 1.000000e+00 -vad_postspeech 50 50 -vad_prespeech 20 20 -vad_startspeech 10 10 -vad_threshold 2.0 2.000000e+00 -var -varfloor 0.0001 1.000000e-04 -varnorm no no -verbose no no -warp_params -warp_type inverse_linear inverse_linear -wbeam 7e-29 7.000000e-29 -wip 0.65 6.500000e-01 -wlen 0.025625 2.562500e-02 INFO: dict.c(320): Allocating 4145 * 32 bytes (129 KiB) for word entries INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/906278D0-92E5-4CCF-A528-516B594EBE4C/Library/Caches/mathModel2.dic INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(336): 39 words read INFO: dict.c(358): Reading filler dictionary: /var/mobile/Containers/Bundle/Application/D1DE9020-50B5-41A9-BC17-28747E4D233B/Converse2.app/AcousticModelEnglish.bundle/noisedict INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones INFO: dict.c(361): 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: fsg_lextree.c(110): Allocated 1410 bytes (1 KiB) for left and right context phones [/spoiler] (lldb) bt * thread #3: tid = 0x1b78a, 0x000000010012fb60 Converse2
fsg_lextree_init + 516, queue = ‘com.apple.root.default-qos’, stop reason = EXC_BAD_ACCESS (code=1, address=0x0)
* frame #0: 0x000000010012fb60 Converse2`fsg_lextree_init + 516
frame #1: 0x0000000100101f08 Converse2`fsg_search_reinit + 92
frame #2: 0x00000001000dacec Converse2`ps_load_dict + 364
frame #3: 0x00000001000ea80c Converse2`___lldb_unnamed_function58$$Converse2 + 428
frame #4: 0x00000001000e9618 Converse2`___lldb_unnamed_function49$$Converse2 + 128
frame #5: 0x00000001000e9214 Converse2`___lldb_unnamed_function42$$Converse2 + 348
frame #6: 0x0000000100459d30 libdispatch.dylib`_dispatch_client_callout + 16
frame #7: 0x000000010047200c libdispatch.dylib`_dispatch_source_latch_and_call + 2848
frame #8: 0x000000010045c2d4 libdispatch.dylib`_dispatch_source_invoke + 808
frame #9: 0x0000000100468908 libdispatch.dylib`_dispatch_root_queue_drain + 760
frame #10: 0x0000000100468600 libdispatch.dylib`_dispatch_worker_thread3 + 132
frame #11: 0x000000019a839478 libsystem_pthread.dylib`_pthread_wqthread + 1092
(lldb)
`October 18, 2015 at 2:55 pm #1027065Halle WinklerPolitepixThanks! Hmm, maybe you are encountering some buggy behavior – the crash looks like it happens when the second dictionary is being initialized, is there anything unusual about the second grammar (i.e. it’s just one word, it has some unusual punctuation, something along those lines)?
October 21, 2015 at 12:03 am #1027076SaliencyParticipantUnfortunately, no, there is no unusual punctuation.
The crash occurs when switching, regardless of whether I start with grammar #1 (which successfully loads initially) and switch to #2, or start with #2 (which also successfully loads initially) and then switch to #1.
Here are the grammars in case you are trying to replicate:
-(void)initializeNormalModel { NSDictionary* grammarDict = @{ ThisWillBeSaidOnce : @[ @{ OneOfTheseWillBeSaidOnce : @[@"HEY "]}, @{ OneOfTheseWillBeSaidOnce : @[@"WHAT TIME IS IT", @"SWITCH TO MATH GRAMMAR"]} ] }; [self saveGrammar:grammarDict withName:@"normalModel2"]; } -(void)initializeMathModel { NSDictionary* grammarDict = @{ ThisWillBeSaidOnce : @[ @{ OneOfTheseWillBeSaidOnce : @[@"HEY "]}, @{ OneOfTheseWillBeSaidOnce : @[@"SWITCH TO NORMAL GRAMMAR", @"CALCULATE" ]}, @{ OneOfTheseCanBeSaidWithOptionalRepetitions: @[@"ONE", @"TWO", @"THREE", @"FOUR", @"FIVE", @"SIX", @"SEVEN", @"EIGHT", @"NINE", @"ZERO", @"OH", @"PLUS", @"TIMES", @"POINT"] }, ] }; [self saveGrammar:grammarDict withName:@"mathModel2"]; }
October 22, 2015 at 10:01 am #1027088Halle WinklerPolitepixThanks, I will check this out after the next update, but I can’t give an estimated time for that unfortunately. I appreciate the notification that there is an issue.
October 22, 2015 at 10:34 pm #1027090SaliencyParticipantThank you. In the meantime is it possible to work around the problem by deallocating and then reallocating the singleton? Is there a tear down procedure I can use?
October 23, 2015 at 9:08 am #1027094Halle WinklerPolitepixHi,
No need to – you can just stop listening and start listening with your next grammar.
October 25, 2015 at 2:32 am #1027107SaliencyParticipantOk — that seems to be working, thanks!
November 12, 2015 at 10:34 pm #1027294mojoParticipantHi, I just wanted to say that I’m having exactly the same problem as Saliency. The above workaround solves the crash, but the stop/start introduces other problems, so it’s not ideal.
November 12, 2015 at 11:56 pm #1027296Halle WinklerPolitepixI agree that it’s a bug and it’s been added to the issues list, but I’d be interested to hear what problems starting and stopping is causing.
November 13, 2015 at 12:10 am #1027298mojoParticipantI should say it can cause other problems. One example would be stopping the controller while flite is still speaking, which would result in AVAudioSession complaining about closing a session on which I/O is still happening resulting in boiler plate code in
fliteDidFinishSpeaking
etc, in other words it could create a mess.November 13, 2015 at 12:22 am #1027301Halle WinklerPolitepixOK, that makes sense that stopping while speech is in progress isn’t ideal, thanks for elaborating.
-
AuthorPosts
- You must be logged in to reply to this topic.