I noticed with pleasure that the new cmusphinx-en-us-ptm-8khz-5.2 PTM acoustic model came out for download, and I can already see that is fast. Since this is a PTM model, what are the relevant exact parameters I should use in order to adapt this 8Khz ptm model? I am trying this configuration:
sphinx_fe:
(same parameters as en-us-8khz)
should I change anything in sphinx_fe other than "-samprate 8000"?
./bw :
-ts2cbfn .ptm.
(leaving the rest of the parameters the same as the en-us-8khz)
should I change anything else in bw other than "-ts2cbfn .ptm." ?
Because I get an error that tells me to check the command line options
FATAL: "mod_inv.c", line 358: Number of feature streams in mixture_weights file 3 differs from the configured value 1, check the command line options
those are my command line options:
Current configuration:
[NAME] [DEFLT] [VALUE]
-2passvar no no
-abeam 1e-100 1.000000e-100
-accumdir /home/AdaptationData/
-agc none none
-agcthresh 2.0 2.000000e+00
-bbeam 1e-100 1.000000e-100
-cb2mllrfn .1cls. .1cls.
-cepdir
-cepext mfc mfc
-ceplen 13 13
-ckptintv 0
-cmn current current
-cmninit 8.0 8.0
-ctlfn /home/AdaptationData/sample.fileids
-diagfull no no
-dictfn /home/Dictionary2
-example no no
-fdictfn
-feat 1s_c_d_dd 1s_c_d_dd
-fullsuffixmatch no no
-fullvar no no
-help no no
-hmmdir /home/cmusphinx-en-us-ptm-8khz-5.2/
-latdir
-latext
-lda
-ldadim 0 0
-lsnfn /home/AdaptationData/sample.transcription
-lw 11.5 1.150000e+01
-maxuttlen 0 0
-meanfn
-meanreest yes yes
-mixwfn
-mixwreest yes yes
-mllrmat
-mmie no no
-mmie_type rand rand
-moddeffn /home/cmusphinx-en-us-ptm-8khz-5.2/mdef
-mwfloor 0.00001 1.000000e-05
-npart 0
-nskip 0
-outphsegdir
-outputfullpath no no
-part 0
-pdumpdir
-phsegdir
-phsegext phseg phseg
-runlen -1 -1
-sentdir
-sentext sent sent
-spthresh 0.0 0.000000e+00
-svspec
-timing yes no
-tmatfn
-tmatreest yes yes
-topn 4 4
-tpfloor 0.0001 1.000000e-04
-ts2cbfn .ptm.
-varfloor 0.00001 1.000000e-05
-varfn
-varnorm no no
-varreest yes yes
-viterbi no no
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I noticed with pleasure that the new cmusphinx-en-us-ptm-8khz-5.2 PTM acoustic model came out for download, and I can already see that is fast. Since this is a PTM model, what are the relevant exact parameters I should use in order to adapt this 8Khz ptm model? I am trying this configuration:
sphinx_fe:
(same parameters as en-us-8khz)
should I change anything in sphinx_fe other than "-samprate 8000"?
./bw :
-ts2cbfn .ptm.
(leaving the rest of the parameters the same as the en-us-8khz)
should I change anything else in bw other than "-ts2cbfn .ptm." ?
Because I get an error that tells me to check the command line options
those are my command line options:
Tutorial has been updated for a new model, you can just follow it.
FATAL: "mod_inv.c", line 358: Number of feature streams in mixture_weights file 3 differs from the configured value 1, check the command line options
./bw \ -hmmdir en-us \ -moddeffn en-us/mdef.txt \ -ts2cbfn .ptm. \ -feat 1s_c_d_dd \ -svspec 0-12/13-25/26-38 \ -cmn current \ -agc none \ -dictfn cmudict-en-us.dict \ -ctlfn wav_recordings.fileids \ -lsnfn wav_recordings.transcription \ -accumdir .
I am using continous model of sphinx4.
Should I change the $CFG_NUM_STREAMS to 4 and then recompile sphinxtrain??
Please help me out on this.