I have question about .wav and train.transcription

[Suwit]

Can I use same transcription, but I add my friend voice for build acoustioc model?

Example..

.lm
hello world

---

.dic
hello H EH L OW
world W ER L D

---

train.transcription
hello (001)
world (002)
hello world (003)
hello (001)
world (002)
hello world (003)

---

train.fileids
myvoice/001
myvoice/002
myvoice/002
friendvoice/001
friendvoice/002
friendvoice/003

---

[Arseniy Gorin]

you better provide unique names for transcription records.
probably the easiest way is to add prefixes to file names

myvoice/myvoice-001
"hello (myvoice-001)"

[Suwit]

Thank you Arseniy Gorin

[Suwit]

I don't understand about error when I train acousic model.
This is my etc and wav files.
https://www.dropbox.com/s/bj2nnhu66u3e54w/th.rar?dl=0

I3asta@I3asta-PC ~/cmusphinx/th
$ sphinxtrain run
Sphinxtrain path: /usr/local/lib/sphinxtrain
Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
Running the training
MODULE: 000 Computing feature from audio files
Extracting features from segments starting at (part 1 of 1)
Extracting features from segments starting at (part 1 of 1)
Feature extraction is done
MODULE: 00 verify training files
Phase 1: Checking to see if the dict and filler dict agrees with the phonelist file.
Found 158 words using 36 phones
Phase 2: Checking to make sure there are not duplicate entries in the dictionary
Phase 3: Check general format for the fileids file; utterance length (must be positive); files exist
Phase 4: Checking number of lines in the transcript file should match lines in fileids file
Phase 5: Determine amount of training data, see if n_tied_states seems reasonable.
Estimated Total Hours Training: 0.594975
This is a small amount of data, no comment at this time
Phase 6: Checking that all the words in the transcript are in the dictionary
Words in dictionary: 155
Words in filler dictionary: 3
Phase 7: Checking that all the phones in the transcript are in the phonelist, and all phones in the phonelist appear at least once
MODULE: 0000 train grapheme-to-phoneme model
Skipped (set $CFG_G2P_MODEL = 'yes' to enable)
MODULE: 01 Train LDA transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 02 Train MLLT transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 05 Vector Quantization
Skipped for continuous models
MODULE: 10 Training Context Independent models for forced alignment and VTLN
Skipped: $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
Skipped: $ST::CFG_VTLN set to 'no' in sphinx_train.cfg
MODULE: 11 Force-aligning transcripts
Skipped: $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
MODULE: 12 Force-aligning data for VTLN
Skipped: $ST::CFG_VTLN set to 'no' in sphinx_train.cfg
MODULE: 20 Training Context Independent models
Phase 1: Cleaning up directories:
accumulator...logs...qmanager...models...
Phase 2: Flat initialize
Phase 3: Forward-Backward
Baum welch starting for 1 Gaussian(s), iteration: 1 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
Normalization for iteration: 1
Current Overall Likelihood Per Frame = -162.93761175773
Baum welch starting for 1 Gaussian(s), iteration: 2 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
Normalization for iteration: 2
Current Overall Likelihood Per Frame = -160.175077384204
Convergence Ratio = 2.76253437352617
Baum welch starting for 1 Gaussian(s), iteration: 3 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 8 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 3
Current Overall Likelihood Per Frame = -153.612100897145
Convergence Ratio = 6.56297648705882
Baum welch starting for 1 Gaussian(s), iteration: 4 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 6 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 4
Current Overall Likelihood Per Frame = -151.408540948568
Convergence Ratio = 2.20355994857684
Baum welch starting for 1 Gaussian(s), iteration: 5 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 24 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 5
Current Overall Likelihood Per Frame = -150.737858343772
Convergence Ratio = 0.670682604796127
Baum welch starting for 1 Gaussian(s), iteration: 6 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 74 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 6
Current Overall Likelihood Per Frame = -150.139403201473
Convergence Ratio = 0.598455142298604
Baum welch starting for 1 Gaussian(s), iteration: 7 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 110 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 7
Current Overall Likelihood Per Frame = -149.536280058695
Convergence Ratio = 0.60312314277806
Baum welch starting for 1 Gaussian(s), iteration: 8 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 152 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 8
Current Overall Likelihood Per Frame = -149.294163836795
Convergence Ratio = 0.242116221899551
Baum welch starting for 1 Gaussian(s), iteration: 9 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 204 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 9
WARNING: WARNING: NEGATIVE CONVERGENCE RATIO AT ITER 9! CHECK BW AND NORM LOGFILES
Current Overall Likelihood Per Frame = -149.458003119633
Training completed after 9 iterations
MODULE: 30 Training Context Dependent models
Phase 1: Cleaning up directories:
accumulator...logs...qmanager...
Phase 2: Initialization
Phase 3: Forward-Backward
Baum welch starting for iteration: 1 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 246 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 1
Current Overall Likelihood Per Frame = -149.585194467099
Baum welch starting for iteration: 2 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 236 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 2
Current Overall Likelihood Per Frame = -146.312275930276
Convergence Ratio = 3.27291853682331
Baum welch starting for iteration: 3 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 228 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 3
Current Overall Likelihood Per Frame = -145.047022110794
Convergence Ratio = 1.26525381948198
Baum welch starting for iteration: 4 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 240 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 4
Current Overall Likelihood Per Frame = -144.776889041995
Convergence Ratio = 0.270133068798543
Baum welch starting for iteration: 5 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 242 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 5
Current Overall Likelihood Per Frame = -144.627634306443
Convergence Ratio = 0.14925473555175
Baum welch starting for iteration: 6 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 246 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 6
Current Overall Likelihood Per Frame = -144.515302800087
Convergence Ratio = 0.112331506356185
Baum welch starting for iteration: 7 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 250 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 7
Current Overall Likelihood Per Frame = -144.43547465202
Training completed after 7 iterations
MODULE: 40 Build Trees
Phase 1: Cleaning up old log files...
Phase 2: Make Questions
Phase 3: Tree building
Processing each phone with each state
AA 0
AA 1
AA 2
AE 0
AE 1
AE 2
AH 0
AH 1
AH 2
AO 0
AO 1
AO 2
AW 0
AW 1
AW 2
AY 0
AY 1
AY 2
B 0
B 1
B 2
CH 0
CH 1
CH 2
D 0
D 1
D 2
ER 0
ER 1
ER 2
EY 0
EY 1
EY 2
H 0
H 1
H 2
IH 0
IH 1
IH 2
IY 0
IY 1
IY 2
J 0
J 1
J 2
K 0
K 1
K 2
L 0
L 1
L 2
M 0
M 1
M 2
N 0
N 1
N 2
NG 0
NG 1
NG 2
NH 0
NH 1
NH 2
OW 0
OW 1
OW 2
OY 0
OY 1
OY 2
P 0
P 1
P 2
PL 0
PL 1
PL 2
R 0
R 1
R 2
S 0
S 1
S 2
SH 0
SH 1
SH 2
Skipping SIL
T 0
T 1
T 2
UA 0
UA 1
UA 2
UE 0
UE 1
UE 2
UH 0
UH 1
UH 2
UW 0
UW 1
UW 2
W 0
W 1
W 2
Y 0
Y 1
Y 2
MODULE: 45 Prune Trees
Phase 1: Tree Pruning
Phase 2: State Tying
MODULE: 50 Training Context dependent models
Phase 1: Cleaning up directories:
accumulator...logs...qmanager...
Phase 2: Copy CI to CD initialize
Phase 3: Forward-Backward
Baum welch starting for 1 Gaussian(s), iteration: 1 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 246 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 1
Current Overall Likelihood Per Frame = -149.585194467099
Baum welch starting for 1 Gaussian(s), iteration: 2 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 236 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 2
Current Overall Likelihood Per Frame = -148.575945604116
Convergence Ratio = 1.00924886298256
Baum welch starting for 1 Gaussian(s), iteration: 3 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 232 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 3
Current Overall Likelihood Per Frame = -148.380488434365
Convergence Ratio = 0.195457169751364
Baum welch starting for 1 Gaussian(s), iteration: 4 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 234 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 4
Current Overall Likelihood Per Frame = -148.259936016746
Convergence Ratio = 0.12055241761928
Baum welch starting for 1 Gaussian(s), iteration: 5 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 234 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 5
Current Overall Likelihood Per Frame = -148.241540055249
Split Gaussians, increase by 1
Current Overall Likelihood Per Frame = -148.241540055249
Convergence Ratio = 0.0183959614973901
Baum welch starting for 2 Gaussian(s), iteration: 1 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 232 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 1
Current Overall Likelihood Per Frame = -148.530429813022
Baum welch starting for 2 Gaussian(s), iteration: 2 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 252 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 2
Current Overall Likelihood Per Frame = -147.314837139976
Convergence Ratio = 1.21559267304568
Baum welch starting for 2 Gaussian(s), iteration: 3 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 282 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 3
Current Overall Likelihood Per Frame = -146.904560834429
Convergence Ratio = 0.410276305547427
Baum welch starting for 2 Gaussian(s), iteration: 4 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 282 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 4
Current Overall Likelihood Per Frame = -146.487933402472
Convergence Ratio = 0.416627431956812
Baum welch starting for 2 Gaussian(s), iteration: 5 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 288 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 5
Current Overall Likelihood Per Frame = -146.343189383615
Convergence Ratio = 0.144744018856812
Baum welch starting for 2 Gaussian(s), iteration: 6 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 264 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 6
Current Overall Likelihood Per Frame = -146.111521276654
Convergence Ratio = 0.231668106961081
Baum welch starting for 2 Gaussian(s), iteration: 7 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 238 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 7
Current Overall Likelihood Per Frame = -145.919291876175
Convergence Ratio = 0.192229400479278
Baum welch starting for 2 Gaussian(s), iteration: 8 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 236 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 8
Current Overall Likelihood Per Frame = -145.84483937846
Split Gaussians, increase by 2
Current Overall Likelihood Per Frame = -145.84483937846
Convergence Ratio = 0.0744524977151855
Baum welch starting for 4 Gaussian(s), iteration: 1 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 232 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 1
Current Overall Likelihood Per Frame = -146.213872524476
Baum welch starting for 4 Gaussian(s), iteration: 2 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 186 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 2
Current Overall Likelihood Per Frame = -144.902801305623
Convergence Ratio = 1.31107121885273
Baum welch starting for 4 Gaussian(s), iteration: 3 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 136 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 3
Current Overall Likelihood Per Frame = -143.756106945591
Convergence Ratio = 1.1466943600324
Baum welch starting for 4 Gaussian(s), iteration: 4 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 142 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 4
Current Overall Likelihood Per Frame = -143.141857103
Convergence Ratio = 0.61424984259051
Baum welch starting for 4 Gaussian(s), iteration: 5 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 154 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 5
Current Overall Likelihood Per Frame = -142.929139555383
Convergence Ratio = 0.212717547616563
Baum welch starting for 4 Gaussian(s), iteration: 6 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 158 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 6
Current Overall Likelihood Per Frame = -142.829640892717
Split Gaussians, increase by 4
Current Overall Likelihood Per Frame = -142.829640892717
Convergence Ratio = 0.09949866266615
Baum welch starting for 8 Gaussian(s), iteration: 1 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 158 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 1
Current Overall Likelihood Per Frame = -143.139663037156
Baum welch starting for 8 Gaussian(s), iteration: 2 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 168 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 2
Current Overall Likelihood Per Frame = -141.988936976619
Convergence Ratio = 1.15072606053687
Baum welch starting for 8 Gaussian(s), iteration: 3 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 176 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 3
Current Overall Likelihood Per Frame = -141.134116702025
Convergence Ratio = 0.854820274594317
Baum welch starting for 8 Gaussian(s), iteration: 4 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 154 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 4
Current Overall Likelihood Per Frame = -140.21922385513
Convergence Ratio = 0.91489284689456
Baum welch starting for 8 Gaussian(s), iteration: 5 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 130 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 5
Current Overall Likelihood Per Frame = -139.628290235819
Convergence Ratio = 0.590933619310874
Baum welch starting for 8 Gaussian(s), iteration: 6 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 122 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 6
Current Overall Likelihood Per Frame = -139.427454645023
Convergence Ratio = 0.200835590796117
Baum welch starting for 8 Gaussian(s), iteration: 7 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 118 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 7
Current Overall Likelihood Per Frame = -139.308395085265
Convergence Ratio = 0.119059559757687
Baum welch starting for 8 Gaussian(s), iteration: 8 (1 of 1)
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
ERROR: This step had 116 ERROR messages and 0 WARNING messages. Please check the log file for details.
Normalization for iteration: 8
Current Overall Likelihood Per Frame = -139.233087306203
Training for 8 Gaussian(s) completed after 8 iterations
MODULE: 60 Lattice Generation
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 61 Lattice Pruning
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 62 Lattice Format Conversion
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 65 MMIE Training
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 90 deleted interpolation
Skipped for continuous models
MODULE: DECODE Decoding using models previously trained
Decoding 1 segments starting at 0 (part 1 of 1)
0% ERROR: FATAL: "batch.c", line 822: PocketSphinx decoder init failed

ERROR: This step had 3 ERROR messages and 0 WARNING messages. Please check the log file for details.
ERROR: Failed to start pocketsphinx_batch
Aligning results to find error rate
Can't open /home/I3asta/cmusphinx/th/result/th-1-1.match
word_align.pl failed with error code 65280 at /usr/local/lib/sphinxtrain/scripts/decode/slave.pl line 173.

[Nickolay V. Shmyrev]

Most of the files you have in your database have very bad quality - the bandwidth is just 2khz, you should have used bad microphone or resampled it somehow. You need to record with better quality.

To deal with such small badwidth you can set in config:

$CFG_NUM_FILT = 13; # For wideband speech it's 25, for telephone 8khz reasonable value is 15
$CFG_LO_FILT = 130; # For telephone 8kHz speech value is 200
$CFG_HI_FILT = 1800; # For telephone 8kHz speech value is 3500

It is better to record properly though.

To learn more about sound bandwidth you can check

http://cmusphinx.sourceforge.net/wiki/faq/#qwhat_is_sample_rate_and_how_does_it_affect_accuracy

[Suwit]

I change config that follow Nickolay V. Shmyrev told me which can build acoustic model sucess but when i test speech it nothing happen. what should i do ? buy a new microphones and new record my voice.

---

$ pocketsphinx_continuous -hmm model_parameters/th.cd_cont_200 -lm th.lm -dict th.dic -inmic yes
INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from model_parameters/th.cd_cont_200/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 live batch
-cmninit 40,3,-1 40,3,-1
-compallsen no no
-debug 0
-dict th.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 model_parameters/th.cd_cont_200
-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 22
-lm th.lm
-lmctl
-lmname
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.300000e+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 13
-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 dct
-unit_area yes yes
-upperf 6855.4976 1.800000e+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: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='batch', VARNORM='no', AGC='none'
INFO: mdef.c(518): Reading model definition: model_parameters/th.cd_cont_200/mdef
INFO: bin_mdef.c(181): Allocating 4756 * 8 bytes (37 KiB) for CD tree
INFO: tmat.c(149): Reading HMM transition probability matrices: model_parameters/th.cd_cont_200/transition_matrices
INFO: acmod.c(113): Attempting to use PTM computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: model_parameters/th.cd_cont_200/means
INFO: ms_gauden.c(242): 308 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x39
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: model_parameters/th.cd_cont_200/variances
INFO: ms_gauden.c(242): 308 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x39
INFO: ms_gauden.c(304): 2 variance values floored
INFO: ptm_mgau.c(804): Number of codebooks exceeds 256: 308
INFO: acmod.c(115): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: model_parameters/th.cd_cont_200/means
INFO: ms_gauden.c(242): 308 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x39
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: model_parameters/th.cd_cont_200/variances
INFO: ms_gauden.c(242): 308 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x39
INFO: ms_gauden.c(304): 2 variance values floored
INFO: acmod.c(117): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: model_parameters/th.cd_cont_200/means
INFO: ms_gauden.c(242): 308 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x39
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: model_parameters/th.cd_cont_200/variances
INFO: ms_gauden.c(242): 308 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 8x39
INFO: ms_gauden.c(304): 2 variance values floored
INFO: ms_senone.c(149): Reading senone mixture weights: model_parameters/th.cd_cont_200/mixture_weights
INFO: ms_senone.c(200): Truncating senone logs3(pdf) values by 10 bits
INFO: ms_senone.c(207): Not transposing mixture weights in memory
INFO: ms_senone.c(268): Read mixture weights for 308 senones: 1 features x 8 codewords
INFO: ms_senone.c(320): Mapping senones to individual codebooks
INFO: ms_mgau.c(144): The value of topn: 4
INFO: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0
INFO: dict.c(320): Allocating 4254 * 32 bytes (132 KiB) for word entries
INFO: dict.c(333): Reading main dictionary: th.dic
INFO: dict.c(213): Dictionary size 155, allocated 1 KiB for strings, 1 KiB for phones
INFO: dict.c(336): 155 words read
INFO: dict.c(358): Reading filler dictionary: model_parameters/th.cd_cont_200/noisedict
INFO: dict.c(213): Dictionary size 158, allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(361): 3 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 36^3 * 2 bytes (91 KiB) for word-initial triphones
INFO: dict2pid.c(132): Allocated 31392 bytes (30 KiB) for word-final triphones
INFO: dict2pid.c(196): Allocated 31392 bytes (30 KiB) for single-phone word triphones
INFO: ngram_model_trie.c(354): Trying to read LM in trie binary format
INFO: ngram_model_trie.c(365): Header doesn't match
INFO: ngram_model_trie.c(177): Trying to read LM in arpa format
INFO: ngram_model_trie.c(193): LM of order 3
INFO: ngram_model_trie.c(195): #1-grams: 157
INFO: ngram_model_trie.c(195): #2-grams: 352
INFO: ngram_model_trie.c(195): #3-grams: 407
INFO: lm_trie.c(474): Training quantizer
INFO: lm_trie.c(482): Building LM trie
INFO: ngram_search_fwdtree.c(74): Initializing search tree
INFO: ngram_search_fwdtree.c(101): 97 unique initial diphones
INFO: ngram_search_fwdtree.c(186): Creating search channels
INFO: ngram_search_fwdtree.c(323): Max nonroot chan increased to 128
INFO: ngram_search_fwdtree.c(333): Created 0 root, 0 non-root channels, 3 single-phone words
INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(307): pocketsphinx_continuous COMPILED ON: Oct 13 2016, AT: 13:31:48

Allocating 32 buffers of 2500 samples each
INFO: continuous.c(252): Ready....
INFO: continuous.c(261): Listening...
INFO: cmn_live.c(120): Update from < 40.00 3.00 -1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 >
INFO: cmn_live.c(138): Update to < 15.67 2.14 -7.09 11.89 0.39 -6.04 12.70 4.77 -0.76 1.02 6.76 1.39 0.18 >
INFO: ngram_search_fwdtree.c(1550): 847 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1552): 978 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1556): 929 channels searched (2/fr), 0 1st, 929 last
INFO: ngram_search_fwdtree.c(1559): 929 words for which last channels evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1561): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1564): fwdtree 0.01 CPU 0.005 xRT
INFO: ngram_search_fwdtree.c(1567): fwdtree 3.45 wall 1.051 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(948): 946 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(950): 981 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(952): 975 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(954): 975 words searched (2/fr)
INFO: ngram_search_fwdflat.c(957): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.00 wall 0.000 xRT
INFO: ngram_search.c(1250): lattice start node .0 end node .276
INFO: ngram_search.c(1276): Eliminated 0 nodes before end node
INFO: ngram_search.c(1381): Lattice has 14 nodes, 17 links
INFO: ps_lattice.c(1380): Bestpath score: -1425
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(:276:326) = -102633
INFO: ps_lattice.c(1441): Joint P(O,S) = -110917 P(S|O) = -8284
INFO: ngram_search.c(872): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(875): bestpath 0.00 wall 0.000 xRT

INFO: continuous.c(275): Ready....
INFO: continuous.c(261): Listening...
INFO: cmn_live.c(120): Update from < 15.67 2.14 -7.09 11.89 0.39 -6.04 12.70 4.77 -0.76 1.02 6.76 1.39 0.18 >
INFO: cmn_live.c(138): Update to < 12.62 3.14 -0.00 18.44 0.27 3.56 13.94 5.02 6.26 2.67 7.69 1.80 1.01 >
INFO: ngram_search_fwdtree.c(1550): 331 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1552): 363 senones evaluated (3/fr)
INFO: ngram_search_fwdtree.c(1556): 357 channels searched (2/fr), 0 1st, 357 last
INFO: ngram_search_fwdtree.c(1559): 357 words for which last channels evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1561): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1564): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1567): fwdtree 1.81 wall 1.486 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(948): 331 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(950): 363 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(952): 357 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(954): 357 words searched (2/fr)
INFO: ngram_search_fwdflat.c(957): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.00 wall 0.000 xRT
INFO: ngram_search.c(1250): lattice start node .0 end node .53
INFO: ngram_search.c(1276): Eliminated 0 nodes before end node
INFO: ngram_search.c(1381): Lattice has 11 nodes, 7 links
INFO: ps_lattice.c(1380): Bestpath score: -398
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(:53:120) = -41611
INFO: ps_lattice.c(1441): Joint P(O,S) = -47328 P(S|O) = -5717
INFO: ngram_search.c(872): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(875): bestpath 0.00 wall 0.000 xRT

INFO: continuous.c(275): Ready....
INFO: continuous.c(261): Listening...

[Suwit]

I bought a new microphone (SAMSON GO MIC). I'm not sure that the my new audio file have good quality. Can you help me to check Audio files that I can use it or not?

https://www.dropbox.com/s/z9kacgvwr3tbd8e/wav.rar?dl=0

Thank you very much.

[Nickolay V. Shmyrev]

Still not perfect, there must be something with your recorder, it seems you record compressed audio and then convert it to wav. You need to use raw audio recorder, like audacity.

[Suwit]

I use audacity for recording now. Can you help me for check it again please?

https://www.dropbox.com/s/dnarbd1xp6gb0tl/testAudio.rar?dl=0

[Nickolay V. Shmyrev]

This is much better. Exactly what needed. Put microphone a bit further from your mouth to avoid random bursts from breath and it will be perfect.

[Suwit]

Thank you very much Nickolay V. Shmyrev. I have a new question. I record new audio files and I used it without error. But when decoding state I found new error about .dmp files.

---

(th1-1.log)

INFO: ngram_model_trie.c(354): Trying to read LM in trie binary format
ERROR: "ngram_model_trie.c", line 356: File /home/I3asta/cmusphinx/th/etc/th.lm.DMP not found
INFO: ngram_model_trie.c(177): Trying to read LM in arpa format
ERROR: "ngram_model_trie.c", line 179: File /home/I3asta/cmusphinx/th/etc/th.lm.DMP not found
INFO: ngram_model_trie.c(445): Trying to read LM in dmp format
ERROR: "ngram_model_trie.c", line 447: Dump file /home/I3asta/cmusphinx/th/etc/th.lm.DMP not found
FATAL: "batch.c", line 822: PocketSphinx decoder init failed
Thu Oct 27 21:27:07 2016

[Nickolay V. Shmyrev]

Your file is called th.lm, not th.lm.DMP, you need to change appropriate line in etc/sphinx_train.cfg:

$DEC_CFG_LANGUAGEMODEL  = "$CFG_BASE_DIR/etc/${CFG_DB_NAME}.lm";

[Suwit]

I think, I haven't enough audio files for train acoustic model.

Phase 5: Determine amount of training data, see if n_tied_states seems reasonable.
Estimated Total Hours Training: 0.770966666666667
This is a small amount of data, no comment at this time

---

Training for 8 Gaussian(s) completed after 7 iterations
MODULE: 60 Lattice Generation
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 61 Lattice Pruning
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 62 Lattice Format Conversion
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 65 MMIE Training
Skipped: $ST::CFG_MMIE set to 'no' in sphinx_train.cfg
MODULE: 90 deleted interpolation
Skipped for continuous models
MODULE: DECODE Decoding using models previously trained
Decoding 150 segments starting at 0 (part 1 of 1)
0%
Aligning results to find error rate
SENTENCE ERROR: 100.0% (150/150) WORD ERROR RATE: 100.0% (150/150)

[Nickolay V. Shmyrev]

I wrote above you need a better language model as well.

[Suwit]

I don't understand. Can you explain me more please?

[Nickolay V. Shmyrev]

You need to collect at least ten megabyte of text data in order to train a good langauge model. Your language model th.lm is not properly trained.

It is better to use more modern toolkit for language model training like SRILM.

[Suwit]

How can I collect at least ten megabyte of text data? If I have 150 word and I
I need to use just 20 sentences. Do I need sort word all possibilities?

I have a new th.lm file to build from SRILM with 32 kilobyte. The results are still sentence and word error 100% .

https://www.dropbox.com/s/bj2nnhu66u3e54w/th.rar?dl=0

For example ( I need to use three sentence for command somthing. )

th.dic

~~~~~~
a A
b B
c C
~~~~

th.txt ---> th.lm

<s> a </s>
<s> a b </s>
<s> a b c </s> I need to use it.
<s> a c b </s>
<s> b </s>
<s> b a </s>
<s> b a c </s> I need to use it.
<s> b c a </s>
<s> c </s>
<s> c a </s>
<s> c a b </s> I need to use it.
<s> c b a </s>

[Suwit]

I still don't understand. This is my problem files th.txt has too little sentences. that show "sentence and word error 100%" or other causes ?
Can i genarator sentence from .dic or I must make a new sentence by my self ?
Sorry Nickolay V. Shmyrev for repeat question

[Nickolay V. Shmyrev]

The problem is that your th.txt th.lm are in windows-874 and your dictionary is in UTF-8 encoding. We recommend to use UTF-8 encoding everywhere.

[Nickolay V. Shmyrev]

If you convert encoding to UTF-8, word error rate would be 6%.

[Suwit]

Thanky you so much Nickolay V. Shmyrev for your advice.

[Suwit]

I can't use acoustic model in Android when I build and run on Sumsung note 2.
The program runs a few moments and then stop down. No error show up ,then I use it in debug mode.
I found the following error :

10/31 14:28:06: Launching app
No apk changes detected since last installation, skipping installation of C:\Users\I3asta\Desktop\pocketsphinx-android-demo-master\app\build\outputs\apk\app-debug.apk
$ adb shell am force-stop edu.cmu.sphinx.pocketsphinx
$ adb shell am start -n "edu.cmu.sphinx.pocketsphinx/edu.cmu.pocketsphinx.demo.PocketSphinxActivity" -a android.intent.action.MAIN -c android.intent.category.LAUNCHER -D
Waiting for application to come online: edu.cmu.sphinx.pocketsphinx.test | edu.cmu.sphinx.pocketsphinx
Connecting to edu.cmu.sphinx.pocketsphinx
I/System.out: Sending WAIT chunk
W/ActivityThread: Application edu.cmu.sphinx.pocketsphinx is waiting for the debugger on port 8100...
I/dalvikvm: Debugger is active
I/System.out: Debugger has connected
I/System.out: waiting for debugger to settle...
I/System.out: waiting for debugger to settle...
I/System.out: waiting for debugger to settle...
Connected to the target VM, address: 'localhost:8600', transport: 'socket'
I/System.out: waiting for debugger to settle...
I/System.out: waiting for debugger to settle...
I/System.out: waiting for debugger to settle...
I/System.out: waiting for debugger to settle...
I/System.out: waiting for debugger to settle...
I/System.out: waiting for debugger to settle...
I/System.out: debugger has settled (1387)
I/InstantRun: Instant Run Runtime started. Android package is edu.cmu.sphinx.pocketsphinx, real application class is null.
W/InstantRun: No instant run dex files added to classpath
I/dalvikvm: Could not find method android.app.Activity.onRequestPermissionsResult, referenced from method edu.cmu.pocketsphinx.demo.PocketSphinxActivity.onRequestPermissionsResult
W/dalvikvm: VFY: unable to resolve virtual method 149: Landroid/app/Activity;.onRequestPermissionsResult (I[Ljava/lang/String;[I)V
D/dalvikvm: VFY: replacing opcode 0x6f at 0x001f
E/MoreInfoHPW_ViewGroup: Parent view is not a TextView
W/ContextImpl: Failed to ensure directory: /storage/extSdCard/Android/data/edu.cmu.sphinx.pocketsphinx/files
I/Assets: Skipping asset th.lm: checksums are equal
D/TextLayoutCache: Enable myanmar Zawgyi converter
I/Assets: Skipping asset th.cd_cont_200/means: checksums are equal
I/Assets: Skipping asset th.filler: checksums are equal
I/Assets: Skipping asset th.txt: checksums are equal
I/Assets: Skipping asset th_train.fileids: checksums are equal
I/Assets: Skipping asset th.cd_cont_200/feat.params: checksums are equal
D/TextLayoutCache: Enable myanmar Zawgyi converter
I/Assets: Skipping asset th_test.fileids: checksums are equal
I/Assets: Skipping asset th.cd_cont_200/transition_matrices: checksums are equal
I/Assets: Skipping asset th.cd_cont_200/variances: checksums are equal
I/Assets: Skipping asset th.cd_cont_200/noisedict: checksums are equal
I/Assets: Skipping asset feat.params: checksums are equal
I/Assets: Skipping asset th.phone: checksums are equal
I/Assets: Skipping asset th.cd_cont_200/mdef: checksums are equal
I/Assets: Skipping asset th.dic: checksums are equal
I/Assets: Skipping asset th_train.transcription: checksums are equal
I/Assets: Skipping asset th.cd_cont_200/assets.lst: checksums are equal
I/Assets: Skipping asset th.cd_cont_200/mixture_weights: checksums are equal
I/Assets: Skipping asset sphinx_train.cfg: checksums are equal
I/Assets: Skipping asset th_test.transcription: checksums are equal
D/libEGL: loaded /system/lib/egl/libEGL_mali.so
D/libEGL: loaded /system/lib/egl/libGLESv1_CM_mali.so
D/libEGL: loaded /system/lib/egl/libGLESv2_mali.so

      [ 10-31 14:28:15.715 13283:13283 E/         ]
      Device driver API match
      Device driver API version: 29
      User space API version: 29

      [ 10-31 14:28:15.715 13283:13283 E/         ]
      mali: REVISION=Linux-r3p2-01rel3 BUILD_DATE=Tue Jul 22 19:59:34 KST 2014

D/dalvikvm: Trying to load lib /data/app-lib/edu.cmu.sphinx.pocketsphinx-31/libpocketsphinx_jni.so 0x424f8c78
D/dalvikvm: Added shared lib /data/app-lib/edu.cmu.sphinx.pocketsphinx-31/libpocketsphinx_jni.so 0x424f8c78
D/dalvikvm: No JNI_OnLoad found in /data/app-lib/edu.cmu.sphinx.pocketsphinx-31/libpocketsphinx_jni.so 0x424f8c78, skipping init
I/cmusphinx: INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from /storage/emulated/0/Android/data/edu.cmu.sphinx.pocketsphinx/files/sync/th.cd_cont_200/feat.params
D/OpenGLRenderer: Enabling debug mode 0
E/cmusphinx: FATAL: "cmn.c", line 126: Unknown CMN type 'batch'
Disconnected from the target VM, address: 'localhost:8600', transport: 'socket'

[Nickolay V. Shmyrev]

Pocketsphinx-android-demo was slighlty outdated. As a temporary fix you can replace "batch" with "current' in model feat.params file.

I also updated pocketsphinx-android-demo from recent soruces, you can clone fresh repo and try again, it should work with your current model.

[Suwit]

Finally, I try sphinx4 import .wav files but the result is " เธ?เธตเน? เธฅเธนเธ?เธชเธฒเธง เธ?เธญเธ? เธ—เน?เธฒเธ? " . I'm sure .dic and .lm are "UTF-8"

---

---

Building STT 1.0-SNAPSHOT

--- exec-maven-plugin:1.2.1:exec (default-cli) @ STT ---
13:19:46.788 INFO unitManager CI Unit: AA
13:19:46.788 INFO unitManager CI Unit: AE
13:19:46.788 INFO unitManager CI Unit: AH
13:19:46.788 INFO unitManager CI Unit: AO
13:19:46.788 INFO unitManager CI Unit: AW
13:19:46.788 INFO unitManager CI Unit: AY
13:19:46.788 INFO unitManager CI Unit: B
13:19:46.788 INFO unitManager CI Unit: CH
13:19:46.788 INFO unitManager CI Unit: D
13:19:46.788 INFO unitManager CI Unit: ER
13:19:46.788 INFO unitManager CI Unit: EY
13:19:46.788 INFO unitManager CI Unit: H
13:19:46.788 INFO unitManager CI Unit: IH
13:19:46.788 INFO unitManager CI Unit: IY
13:19:46.788 INFO unitManager CI Unit: J
13:19:46.788 INFO unitManager CI Unit: K
13:19:46.803 INFO unitManager CI Unit: L
13:19:46.803 INFO unitManager CI Unit: M
13:19:46.803 INFO unitManager CI Unit: N
13:19:46.803 INFO unitManager CI Unit: NG
13:19:46.803 INFO unitManager CI Unit: NH
13:19:46.803 INFO unitManager CI Unit: OW
13:19:46.803 INFO unitManager CI Unit: OY
13:19:46.803 INFO unitManager CI Unit: P
13:19:46.803 INFO unitManager CI Unit: PL
13:19:46.803 INFO unitManager CI Unit: R
13:19:46.803 INFO unitManager CI Unit: S
13:19:46.803 INFO unitManager CI Unit: SH
13:19:46.803 INFO unitManager CI Unit: T
13:19:46.803 INFO unitManager CI Unit: UA
13:19:46.803 INFO unitManager CI Unit: UE
13:19:46.803 INFO unitManager CI Unit: UH
13:19:46.803 INFO unitManager CI Unit: UW
13:19:46.803 INFO unitManager CI Unit: W
13:19:46.803 INFO unitManager CI Unit: Y
13:19:46.944 INFO autoCepstrum Cepstrum component auto-configured as follows: autoCepstrum {MelFrequencyFilterBank, Denoise, DiscreteCosineTransform2, Lifter}
13:19:46.944 INFO dictionary Loading dictionary from: file:/C:/Users/I3asta/Documents/NetBeansProjects/STT/target/classes/th.dic
13:19:46.944 INFO dictionary Loading filler dictionary from: file:/C:/Users/I3asta/Documents/NetBeansProjects/STT/target/classes/th.cd_cont_200/noisedict
13:19:46.944 INFO acousticModelLoader Loading tied-state acoustic model from: file:/C:/Users/I3asta/Documents/NetBeansProjects/STT/target/classes/th.cd_cont_200
13:19:46.944 INFO acousticModelLoader Pool means Entries: 2464
13:19:46.944 INFO acousticModelLoader Pool variances Entries: 2464
13:19:46.944 INFO acousticModelLoader Pool transition_matrices Entries: 36
13:19:46.944 INFO acousticModelLoader Pool senones Entries: 308
13:19:46.944 INFO acousticModelLoader Gaussian weights: mixture_weights. Entries: 308
13:19:46.960 INFO acousticModelLoader Pool senones Entries: 308
13:19:46.960 INFO acousticModelLoader Context Independent Unit Entries: 36
13:19:46.960 INFO acousticModelLoader HMM Manager: 4017 hmms
13:19:46.960 INFO acousticModel CompositeSenoneSequences: 0
13:19:46.960 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธ?เธถเน?เธ?'
13:19:46.960 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธขเน?เธญเธข'
13:19:46.960 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธชเธดเธ?'
13:19:46.960 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธขเน?เธญเธข'
13:19:46.975 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธ?เธถเน?เธ?'
13:19:46.975 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธ?เธถเน?เธ?'
13:19:46.975 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธขเน?เธญเธข'
13:19:46.975 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธชเธดเธ?'
13:19:46.975 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธชเธดเธ?'
13:19:47.209 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธชเธดเธ?'
13:19:47.209 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธ?เธถเน?เธ?'
13:19:47.209 INFO dictionary The dictionary is missing a phonetic transcription for the word 'เธขเน?เธญเธข'
13:19:47.240 INFO lexTreeLinguist Max CI Units 37
13:19:47.240 INFO lexTreeLinguist Unit table size 50653
13:19:47.240 INFO speedTracker # ----------------------------- Timers----------------------------------------
13:19:47.240 INFO speedTracker # Name Count CurTime MinTime MaxTime AvgTime TotTime
13:19:47.240 INFO speedTracker Load AM 1 0.2030s 0.2030s 0.2030s 0.2030s 0.2030s
13:19:47.240 INFO speedTracker Load Dictionary 1 0.0000s 0.0000s 0.0000s 0.0000s 0.0000s
13:19:47.240 INFO speedTracker Compile 1 0.2490s 0.2490s 0.2490s 0.2490s 0.2490s
13:19:47.553 INFO liveCMN 35.37 17.23 7.54 -9.55 -4.68 -5.06 4.82 7.70 -0.17 2.43 5.90 -6.93 5.58
13:19:47.631 INFO speedTracker This Time Audio: 2.73s Proc: 0.34s Speed: 0.13 X real time
13:19:47.631 INFO speedTracker Total Time Audio: 2.73s Proc: 0.34s 0.13 X real time
13:19:47.631 INFO memoryTracker Mem Total: 152.50 Mb Free: 125.29 Mb
13:19:47.631 INFO memoryTracker Used: This: 27.21 Mb Avg: 27.21 Mb Max: 27.21 Mb
Hypothesis: เธ?เธตเน? เธฅเธนเธ?เธชเธฒเธง เธ?เธญเธ? เธ—เน?เธฒเธ?
13:19:47.646 INFO liveCMN 35.25 17.31 7.70 -9.53 -4.79 -5.09 4.88 7.93 -0.10 2.58 5.91 -6.77 5.52
13:19:47.678 INFO speedTracker This Time Audio: 0.48s Proc: 0.03s Speed: 0.07 X real time
13:19:47.678 INFO speedTracker Total Time Audio: 3.21s Proc: 0.38s 0.12 X real time
13:19:47.678 INFO memoryTracker Mem Total: 152.50 Mb Free: 112.32 Mb
13:19:47.678 INFO memoryTracker Used: This: 40.18 Mb Avg: 33.70 Mb Max: 40.18 Mb
Hypothesis: เธ?เน?เธญเธ?
13:19:47.693 INFO liveCMN 34.44 17.23 5.80 -9.92 -3.23 -3.11 5.64 7.10 -0.86 2.40 6.30 -7.92 4.73
13:19:47.709 INFO speedTracker This Time Audio: 0.36s Proc: 0.03s Speed: 0.09 X real time
13:19:47.709 INFO speedTracker Total Time Audio: 3.57s Proc: 0.41s 0.11 X real time
13:19:47.709 INFO memoryTracker Mem Total: 152.50 Mb Free: 103.24 Mb
13:19:47.709 INFO memoryTracker Used: This: 49.26 Mb Avg: 38.88 Mb Max: 49.26 Mb
Hypothesis:
13:19:47.725 INFO speedTracker This Time Audio: 0.42s Proc: 0.02s Speed: 0.04 X real time
13:19:47.725 INFO speedTracker Total Time Audio: 3.99s Proc: 0.42s 0.11 X real time
13:19:47.725 INFO memoryTracker Mem Total: 152.50 Mb Free: 90.26 Mb
13:19:47.725 INFO memoryTracker Used: This: 62.24 Mb Avg: 44.72 Mb Max: 62.24 Mb
Hypothesis: เธ?เธฐ
13:19:47.725 INFO speedTracker # ----------------------------- Timers----------------------------------------
13:19:47.725 INFO speedTracker # Name Count CurTime MinTime MaxTime AvgTime TotTime
13:19:47.725 INFO speedTracker Load AM 1 0.2030s 0.2030s 0.2030s 0.2030s 0.2030s
13:19:47.725 INFO speedTracker Frontend 484 0.0000s 0.0000s 0.0470s 0.0002s 0.1110s
13:19:47.725 INFO speedTracker Load Dictionary 1 0.0000s 0.0000s 0.0000s 0.0000s 0.0000s
13:19:47.725 INFO speedTracker Compile 1 0.2490s 0.2490s 0.2490s 0.2490s 0.2490s
13:19:47.725 INFO speedTracker Score 956 0.0000s 0.0000s 0.0470s 0.0002s 0.1580s
13:19:47.725 INFO speedTracker Prune 3336 0.0000s 0.0000s 0.0000s 0.0000s 0.0000s
13:19:47.725 INFO speedTracker Grow 3346 0.0000s 0.0000s 0.0160s 0.0001s 0.2500s
13:19:47.725 INFO speedTracker Total Time Audio: 3.99s Proc: 0.42s 0.11 X real time
13:19:47.725 INFO memoryTracker Mem Total: 152.50 Mb Free: 90.26 Mb
13:19:47.725 INFO memoryTracker Used: This: 62.24 Mb Avg: 48.23 Mb Max: 62.24 Mb
------------------------------------------------------------------------
BUILD SUCCESS
------------------------------------------------------------------------
Total time: 2.375s
Finished at: Fri Nov 04 13:19:48 ICT 2016
Final Memory: 5M/120M
------------------------------------------------------------------------

[Nickolay V. Shmyrev]

You also need to set JVM file encoding probably with an option -Dfile.encoding=UTF-8