VoxForge
VoxForge
Hi
I want to do livedecodeing.
when I run sphnx3_livedecode I got this.
Usage: livedecode config_file
In sphinx4 we have demo programs for testing.
I tried to run sphinx3_livedecode, but it asks for input 'config_file'. How can I construct it or find it ? Could anyone give me a demo example to test Sphinx3
Thank u
--- (Edited on 8/1/2009 11:17 pm [GMT-0500] by Visitor) ---
Hi dss,
>Could anyone give me a demo example to test Sphinx3
see the CMU Robust Group Tutorial
Ken
--- (Edited on 8/6/2009 10:59 am [GMT-0400] by kmaclean) ---
Here is the best info I've found: http://sphinx.subwiki.com/sphinx/index.php/Hello_World_Decoder_QuickStart_Guide
We must create a config file of the form:
-samprate 16000 -hmm $SPHINX_ROOT/sphinx3/model/hmm/hub4_cd_continuous_8gau_1s_c_d_dd -dict $SPHINX_ROOT/lm_giga_5k_nvp_3gram/lm_giga_5k_nvp.sphinx.dic -fdict $SPHINX_ROOT/lm_giga_5k_nvp_3gram/lm_giga_5k_nvp.sphinx.filler -lm $SPHINX_ROOT/lm_giga_5k_nvp_3gram/lm_giga_5k_nvp_3gram.arpa.DMP
However I'm not yet sure of the parameters for voxforge.
Anyone know? Shouldnt this config file be included in the voxforge sphinx package?
I was not able to find the information in the URL Ken posted.
Thanks
--- (Edited on 8/27/2009 1:27 am [GMT-0500] by ) ---
--- (Edited on 8/27/2009 1:34 am [GMT-0500] by ) ---
Update. Got it working. Here are the steps.
Follow the instructions in the URL in my last message to generate a DMP from the lm_giga_5k_nvp language model.
Copy the VoxForge acoustic models, and lm_giga_5k_nvp language models & dictionarys, to the same directory.
Create the following cfg.txt:
-samprate 16000
-hmm model_parameters/voxforge_en_sphinx.mllt_cd_cont_3000
-dict lm_giga_5k_nvp_3gram/lm_giga_5k_nvp.sphinx.dic
-fdict lm_giga_5k_nvp_3gram/lm_giga_5k_nvp.sphinx.filler
-lm lm_giga_5k_nvp_3gram/lm_giga_5k_nvp_3gram.arpa.DMP
Run: sphinx3_livedecode cfg.txt !
press ENTER to start recording
Partial hypothesis:
this is the future
--- (Edited on 8/27/2009 1:14 pm [GMT-0500] by ) ---
I have done as your steps ,but failed . the log:
INFO: cmd_ln.c(512): Parsing command line:
\
-samprate 16000 \
-hmm D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000 \
-dict D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.dic \
-fdict D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.filler \
-lm D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp_3gram.arpa.DMP
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+000
-alpha 0.97 9.700000e-001
-backtrace yes yes
-beam 1.0e-55 1.000000e-055
-bestpath no no
-bestpathlw 0.000000e+000
-bestscoredir
-bestsenscrdir
-bghist no no
-bptbldir
-bptblsize 32768 32768
-cb2mllr .1cls. .1cls.
-ceplen 13 13
-ci_pbeam 1e-80 1.000000e-080
-cmn current current
-cmninit 8.0 8.0
-cond_ds no no
-ctl
-ctlcount 1000000000 1000000000
-ctloffset 0 0
-ctl_lm
-ctl_mllr
-dagfudge 2 2
-dict D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.dic
-dist_ds no no
-dither no no
-doublebw no no
-ds 1 1
-epl 3 3
-fdict D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.filler
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
-fillpen
-fillprob 0.1 1.000000e-001
-frate 100 100
-fsg
-fsgusealtpron yes yes
-fsgusefiller yes yes
-gs
-gs4gs yes yes
-hmm D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000
-hmmdump no no
-hmmdumpef 200000000 200000000
-hmmdumpsf 200000000 200000000
-hmmhistbinsize 5000 5000
-hyp
-hypseg
-hypsegscore_unscale yes yes
-inlatdir
-inlatwin 50 50
-input_endian little little
-kdmaxbbi -1 -1
-kdmaxdepth 0 0
-kdtree
-latcompress yes yes
-latext lat.gz lat.gz
-lda
-ldadim 0 0
-lextreedump 0 0
-lifter 0 0
-lm D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp_3gram.arpa.DMP
-lmctlfn
-lmdumpdir
-lmname
-log3table yes yes
-logbase 1.0003 1.000300e+000
-logspec no no
-lowerf 133.33334 1.333333e+002
-lts_mismatch no no
-lw 9.5 9.500000e+000
-machine_endian little little
-maxcdsenpf 100000 100000
-maxedge 2000000 2000000
-maxhistpf 100 100
-maxhmmpf 20000 20000
-maxhyplen 1000 1000
-maxlmop 100000000 100000000
-maxlpf 40000 40000
-maxppath 1000000 1000000
-maxwpf 20 20
-mdef
-mdef_fillers no no
-mean
-min_endfr 3 3
-mixw
-mixwfloor 0.0000001 1.000000e-007
-mllr
-mode fwdtree fwdtree
-nbest 200 200
-nbestdir
-nbestext nbest.gz nbest.gz
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-Nlextree 3 3
-Nstalextree 25 25
-op_mode -1 -1
-outlatdir
-outlatfmt s3 s3
-pbeam 1.0e-50 1.000000e-050
-pheurtype 0 0
-phonepen 1.0 1.000000e+000
-phypdump yes yes
-pl_beam 1.0e-80 1.000000e-080
-pl_window 1 1
-ppathdebug no no
-ptranskip 0 0
-rawext .raw .raw
-remove_dc no no
-round_filters yes yes
-samprate 16000 1.600000e+004
-seed -1 -1
-sendump
-senmgau .cont. .cont.
-silprob 0.1 1.000000e-001
-smoothspec no no
-subvq
-subvqbeam 3.0e-3 3.000000e-003
-svq4svq no no
-svspec
-tighten_factor 0.5 5.000000e-001
-tmat
-tmatfloor 0.0001 1.000000e-004
-topn 4 4
-topn_beam 0 0
-tracewhmm
-transform legacy legacy
-treeugprob yes yes
-unit_area yes yes
-upperf 6855.4976 6.855498e+003
-uw 0.7 7.000000e-001
-var
-varfloor 0.0001 1.000000e-004
-varnorm no no
-verbose no no
-vqeval 3 3
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 1.0e-35 1.000000e-035
-wend_beam 1.0e-80 1.000000e-080
-wip 0.7 7.000000e-001
-wlen 0.025625 2.562500e-002
-worddumpef 200000000 200000000
-worddumpsf 200000000 200000000
INFO: kbcore.c(446): Begin Initialization of Core Models:
INFO: cmd_ln.c(512): Parsing command line:
\
-alpha 0.97 \
-dither yes \
-doublebw no \
-nfilt 40 \
-ncep 13 \
-lowerf 133.33334 \
-upperf 6855.4976 \
-nfft 512 \
-wlen 0.0256 \
-transform legacy \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-varnorm no
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+000
-alpha 0.97 9.700000e-001
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-dither no yes
-doublebw no no
-feat 1s_c_d_dd 1s_c_d_dd
-frate 100 100
-input_endian little little
-lda
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 1.333333e+002
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-remove_dc no no
-round_filters yes yes
-samprate 16000 1.600000e+004
-seed -1 -1
-smoothspec no no
-svspec
-transform legacy legacy
-unit_area yes yes
-upperf 6855.4976 6.855498e+003
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.560000e-002
INFO: Initialization of the log add table
INFO: Log-Add table size = 29356 x 2 >> 0
INFO:
INFO: feat.c(848): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: kbcore.c(493): .cont.
INFO: Initialization of feat_t, report:
INFO: Feature type = 1s_c_d_dd
INFO: Cepstral size = 13
INFO: Number of streams = 1
INFO: Vector size of stream[0]: 39
INFO: Number of subvectors = 0
INFO: Whether CMN is used = 1
INFO: Whether AGC is used = 0
INFO: Whether variance is normalized = 0
INFO:
INFO: Reading Feature Space Transform from: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/feature_transform
INFO: Reading HMM in Sphinx 3 Model format
INFO: Model Definition File: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/mdef
INFO: Mean File: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/means
INFO: Variance File: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/variances
INFO: Mixture Weight File: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/mixture_weights
INFO: Transition Matrices File: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/transition_matrices
INFO: mdef.c(687): Reading model definition: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/mdef
INFO: Initialization of mdef_t, report:
INFO: 40 CI-phone, 100516 CD-phone, 3 emitstate/phone, 120 CI-sen, 3120 Sen, 18846 Sen-Seq
INFO:
INFO: kbcore.c(303): Using optimized GMM computation for Continuous HMM, -topn will be ignored
INFO: cont_mgau.c(170): Reading mixture gaussian file 'D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/means'
INFO: cont_mgau.c(429): 3120 mixture Gaussians, 16 components, 1 streams, veclen 29
INFO: cont_mgau.c(170): Reading mixture gaussian file 'D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/variances'
INFO: cont_mgau.c(429): 3120 mixture Gaussians, 16 components, 1 streams, veclen 29
INFO: cont_mgau.c(530): Reading mixture weights file 'D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/mixture_weights'
INFO: cont_mgau.c(685): Read 3120 x 16 mixture weights
INFO: cont_mgau.c(713): Removing uninitialized Gaussian densities
INFO: cont_mgau.c(803): Applying variance floor
INFO: cont_mgau.c(821): 63 variance values floored
INFO: cont_mgau.c(869): Precomputing Mahalanobis distance invariants
INFO: tmat.c(170): Reading HMM transition probability matrices: D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000/transition_matrices
INFO: Initialization of tmat_t, report:
INFO: Read 40 transition matrices of size 3x4
INFO:
INFO: dict.c(386): Reading main dictionary: D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.dic
ERROR: "dict.c", line 266: Line 1: Bad ciphone: ah; word a ignored
ERROR: "dict.c", line 266: Line 2: Bad ciphone: ey; word a(2) ignored
ERROR: "dict.c", line 266: Line 3: Bad ciphone: ey; word a. ignored
ERROR: "dict.c", line 266: Line 4: Bad ciphone: ey; word a.'s ignored
ERROR: "dict.c", line 266: Line 5: Bad ciphone: ah; word abandoned ignored
ERROR: "dict.c", line 266: Line 6: Bad ciphone: ae; word abdul ignored
ERROR: "dict.c", line 266: Line 7: Bad ciphone: ae; word abdullah ignored
ERROR: "dict.c", line 266: Line 8: Bad ciphone: ah; word ability ignored
ERROR: "dict.c", line 266: Line 9: Bad ciphone: ey; word able ignored
ERROR: "dict.c", line 266: Line 10: Bad ciphone: ah; word aboard ignored
ERROR: "dict.c", line 266: Line 11: Bad ciphone: ah; word abortion ignored
ERROR: "dict.c", line 266: Line 12: Bad ciphone: ah; word about ignored
ERROR: "dict.c", line 266: Line 13: Bad ciphone: ah; word above ignored
ERROR: "dict.c", line 266: Line 14: Bad ciphone: ah; word abroad ignored
ERROR: "dict.c", line 266: Line 15: Bad ciphone: ae; word absence ignored
ERROR: "dict.c", line 266: Line 16: Bad ciphone: ae; word absolutely ignored
ERROR: "dict.c", line 266: Line 17: Bad ciphone: ae; word abu ignored
ERROR: "dict.c", line 266: Line 18: Bad ciphone: ah; word abuse ignored
ERROR: "dict.c", line 266: Line 19: Bad ciphone: ah; word abuse(2) ignored
ERROR: "dict.c", line 266: Line 20: Bad ciphone: ah; word abuses ignored
ERROR: "dict.c", line 266: Line 21: Bad ciphone: ah; word abuses(2) ignored
ERROR: "dict.c", line 266: Line 22: Bad ciphone: ae; word academic ignored
ERROR: "dict.c", line 266: Line 23: Bad ciphone: ah; word academy ignored
....
ERROR: "dict.c", line 266: Line 5892: Bad ciphone: z; word zemin ignored
ERROR: "dict.c", line 266: Line 5893: Bad ciphone: z; word zero ignored
ERROR: "dict.c", line 266: Line 5894: Bad ciphone: z; word zero(2) ignored
ERROR: "dict.c", line 266: Line 5895: Bad ciphone: zh; word zhang ignored
ERROR: "dict.c", line 266: Line 5896: Bad ciphone: zh; word zhang(2) ignored
ERROR: "dict.c", line 266: Line 5897: Bad ciphone: z; word zhu ignored
ERROR: "dict.c", line 266: Line 5898: Bad ciphone: z; word zimbabwe ignored
ERROR: "dict.c", line 266: Line 5899: Bad ciphone: z; word zone ignored
ERROR: "dict.c", line 266: Line 5900: Bad ciphone: z; word zones ignored
INFO: dict.c(389): 0 words read
INFO: dict.c(394): Reading filler dictionary: D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.filler
ERROR: "dict.c", line 266: Line 1: Bad ciphone: sil; word <s> ignored
ERROR: "dict.c", line 266: Line 2: Bad ciphone: sil; word </s> ignored
ERROR: "dict.c", line 266: Line 3: Bad ciphone: sil; word <sil> ignored
.....
INFO: dict.c(397): 0 words read
INFO: dict.c(430): Added 0 fillers from mdef file
INFO: Initialization of dict_t, report:
INFO: No of CI phone: 0
INFO: Max word: 9999
INFO: No of word: 3
INFO:
INFO: lm.c(613): LM read('D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp_3gram.arpa.DMP', lw= 9.50, wip= 0.70, uw= 0.70)
INFO: lm.c(615): Reading LM file D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp_3gram.arpa.DMP (LM name "default")
INFO: lm_3g_dmp.c(632): Reading LM in 16 bits format
INFO: lm_3g_dmp.c(688): Read 5000 unigrams [in memory]
INFO: lm_3g_dmp.c(761): 2821547 bigrams [on disk]
INFO: lm_3g_dmp.c(834): 8095821 bigrams [on disk]
INFO: lm_3g_dmp.c(904): 33667 bigram prob entries
INFO: lm_3g_dmp.c(938): 14145 trigram bowt entries
INFO: lm_3g_dmp.c(969): 35722 trigram prob entries
INFO: lm_3g_dmp.c(1000): 5511 trigram segtable entries (512 segsize)
INFO: lm_3g_dmp.c(1055): 5000 word strings
INFO: lm.c(711): The LM routine is operating at 16 bits mode
ERROR: "wid.c", line 282: <unk> is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: a is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: a. is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: a.'s is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: abandoned is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: abdul is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: abdullah is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: ability is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: zhu is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: zimbabwe is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: zone is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: zones is not a word in dictionary and it is not a class tag.
INFO: wid.c(292): 4998 LM words not in dictionary; ignored
INFO: Initialization of fillpen_t, report:
INFO: Language weight =9.500000
INFO: Word Insertion Penalty =0.700000
INFO: Silence probability =0.100000
INFO: Filler probability =0.100000
INFO:
INFO: dict2pid.c(601): Building PID tables for dictionary
INFO: Initialization of dict2pid_t, report:
INFO: Dict2pid is in composite triphone mode
INFO: 3 composite states; 1 composite sseq
INFO:
INFO: kbcore.c(639): Inside kbcore: Verifying models consistency ......
INFO: kbcore.c(661): End of Initialization of Core Models:
ERROR: "cmd_ln.c", line 879: Unknown argument: -debug
INFO: Initialization of beam_t, report:
INFO: Parameters used in Beam Pruning of Viterbi Search:
INFO: Beam=-422203
INFO: PBeam=-383821
INFO: WBeam=-268675 (Skip=0)
INFO: WEndBeam=-614114
INFO: No of CI Phone assumed=40
INFO:
INFO: Initialization of fast_gmm_t, report:
INFO: Parameters used in Fast GMM computation:
INFO: Frame-level: Down Sampling Ratio 1, Conditional Down Sampling? 0, Distance-based Down Sampling? 0
INFO: GMM-level: CI phone beam -614114. MAX CD 100000
INFO: Gaussian-level: GS map would be used for Gaussian Selection? =1, SVQ would be used as Gaussian Score? =0 SubVQ Beam -19366
INFO:
INFO: Initialization of pl_t, report:
INFO: Parameters used in phoneme lookahead:
INFO: Phoneme look-ahead type = 0
INFO: Phoneme look-ahead beam size = -614114
INFO: No of CI Phones assumed=40
INFO:
INFO: Initialization of ascr_t, report:
INFO: No. of CI senone =120
INFO: No. of senone = 3120
INFO: No. of composite senone = 3
INFO: No. of senone sequence = 18846
INFO: No. of composite senone sequence=1
INFO: Parameters used in phoneme lookahead:
INFO: Phoneme lookahead window = 1
INFO:
INFO: kb.c(308): SEARCH MODE INDEX 4
INFO: srch.c(377): Search Initialization.
INFO: srch_time_switch_tree.c(286): -Nstalextree is omitted in TST search.
INFO: lextree.c(226): Creating Unigram Table for lm (name: default)
INFO: lextree.c(239): Size of word table after unigram + words in class: 0.
FATAL_ERROR: "lextree.c", line 243: 0 active words in default
--- (Edited on 12/1/2010 4:14 am [GMT-0600] by danielchen) ---
Hello
The reason of the error is explained in the log, you just need to read it:
ERROR: "dict.c", line 266: Line 1: Bad ciphone: ah; word a ignored
The error is caused by mismatch between the dictionary and the acoustic model. Acoustic model uses upper-case phones like AH IH EH and dictionary use lower-case models like ah eh ih. You need to get proper dictionary or convert existing dictionary yourself to the proper format. That can be done with simple script.
Please note that while phones needs to be uppercase, words needs to be lowercase, so you need to convert only phone names
For futher questions on CMUSphinx I recommend you to use CMUSphinx forums
--- (Edited on 12/1/2010 15:47 [GMT+0300] by nsh) ---
INFO: cmd_ln.c(512): Parsing command line:
\
-samprate 16000 \
-hmm D:\sphinx3\run_demo\voxforge_en_sphinx.mllt_cd_cont_3000 \
-dict D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.dic \
-fdict D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp.sphinx.filler \
-lm D:\sphinx3\run_demo\lm_giga_5k_nvp_3gram\lm_giga_5k_nvp_3gram.arpa.DMP
i have convert lowercase to up_case for the files: lm_giga_5k_nvp.sphinx.dic lm_giga_5k_nvp.sphinx.filler,
but it still failed .
error info :
ERROR: "wid.c", line 282: violations is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: violence is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: violent is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: virginia is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: virtually is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: virus is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: visa is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: vision is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: visit is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: visited is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: visiting is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: visitors is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: visits is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: vital is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: vladimir is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: voice is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: volume is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: volunteers is not a word in dictionary and it is not a class tag.
ERROR: "wid.c", line 282: vote is not a word in dictionary and it is not a class tag.
--- (Edited on 12/2/2010 12:58 am [GMT-0600] by danielchen) ---
> i have convert lowercase to up_case for the files: lm_giga_5k_nvp.sphinx.dic lm_giga_5k_nvp.sphinx.filler, but it still failed . You need to read my reply carefully Please note that while phones needs to be uppercase, words needs to be lowercase, so you need to convert only phone names You can find dictionary in proper format here:
--- (Edited on 12/2/2010 12:14 [GMT+0300] by nsh) ---