I have an Android phone recording of a meeting that I'd like to
transcribe to text, and was hoping there was an automagic way to convert
most of it.
My google-fu seems to be failing me, or else that info simply isn't out
there.
The closest I've found is the use of a tool called pocketsphinx (which
seems to be a toolset for developers to be used in applications, not a
finished product suitable for use by an end-user).
I saved my Android audio file to Google Drive, and downloaded it from
there to my main Debian box (for unknown reasons, I couldn't use GMail
to mail it as an attachment, or attach it to an FB Message).
As per what I was able to figure out about it, I then converted my .mp4
file to a .wav file:
ffmpeg -i ../Downloads/Dana\ of\ City.m4a -ar 16000 -ac 1 DanaOfCity.wav
I verified that worked with
aplay DanaOfCity.wav
Then I worked out the basics (I hoped) of the command to be this (mostly
from an example at
https://askubuntu.com/questions/161515/speech-recognition-app-to-convert-mp3-to-text
(answer 8, footnote 2):
pocketsphinx_continuous -infile ~/Downloads/DanaOfCity.wav -hmm
en_US/hub4wsj_sc_8k -lm en_US/hub4.5000.DMP 2> pocketsphinx.log
which I understand to mean:
- my input file is my data file "DanaOfCity.wav"
- the "-hmm" parameter (which pocketsphinx knows automatically is in
/usr/share/pocketsphinx/model) is to be the "en_US/hub4wwsj_sc_8k"
directory (which contains the "mdef" model (whatever that is), which it
had trouble finding until I added the "hub..." part)
- the "-lm" (is that a digit one or a letter ell? ah, it's an ell)
parameter works like the "-hmm" parameter above
- the 2> pocketsphinx.log routes the normal output of the app to a file
named "pocketsphinx.log" in the current directory
When I run this, the process files with this output in my
pocketsphinx.log output:
westk@westek:~/bub$ cat pocketsphinx.log
INFO: pocketsphinx.c(145): Parsed model-specific feature parameters from
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/feat.params
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 56,-3,1
-compallsen no no
-debug 0
-dict
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict /usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/noisedict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/feat.params
-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 /usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k
-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 /usr/share/pocketsphinx/model/lm/en_US/hub4.5000.DMP
-lmctl
-lmname
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.000000e+00
-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 /usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/mdef
-mean /usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/means
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-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 yes
-remove_noise yes yes
-remove_silence yes yes
-round_filters yes no
-samprate 16000 1.600000e+04
-seed -1 -1
-sendump /usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec 0-12/13-25/26-38
-tmat
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 4.000000e+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 /usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/variances
-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 2.500000e-02
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(164): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(518): Reading model definition:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/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:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/mdef
INFO: bin_mdef.c(516): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone,
150 CI-sen, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(206): Reading HMM transition probability matrices:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/transition_matrices
INFO: acmod.c(117): Attempting to use PTM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
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 != 50
INFO: acmod.c(119): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(294): 256x13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(904): Loading senones from dump file
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/sendump
INFO: s2_semi_mgau.c(928): BEGIN FILE FORMAT DESCRIPTION
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 4107 * 32 bytes (128 KiB) for word entries
INFO: dict.c(358): Reading filler dictionary:
/usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/noisedict
INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(361): 11 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 50^3 * 2 bytes (244 KiB) for
word-initial triphones
INFO: dict2pid.c(132): Allocated 60400 bytes (58 KiB) for word-final
triphones
INFO: dict2pid.c(196): Allocated 60400 bytes (58 KiB) for single-phone
word triphones
INFO: ngram_model_trie.c(456): Trying to read LM in trie binary format
INFO: ngram_model_trie.c(467): Header doesn't match
INFO: ngram_model_trie.c(189): Trying to read LM in arpa format
INFO: ngram_model_trie.c(70): No \data\ mark in LM file
INFO: ngram_model_trie.c(548): Trying to read LM in DMP format
INFO: ngram_model_trie.c(630): ngrams 1=5001, 2=436879, 3=418286
pocketsphinx_continuous: ngrams_raw.c:372: ngrams_raw_read_dmp:
Assertion `ngram_idx == counts[2]' failed.
Anyone out there who can help me accomplish my goal, using pocketsphinx
or any other suitable tool?
Thanks!
--
Kent West <*)))><
http://kentwest.blogspot.com
Praise Yah! \o/