I am training an acoustic model. I getting error while running following command
python sphinxtrain-win32/scripts/sphinxtrain run
output is as follows :-
MODULE: 000 Computing feature from audio files
Extracting features from segments starting at (part 1 of 1)
This step had 1 ERROR messages and 0 WARNING messages. Please check the log file for details.
Extracting features from segments starting at (part 1 of 1)
This step had 1 ERROR messages and 0 WARNING messages. Please check the log file for details.
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 14 words using 17 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: 0.00234166666666667
WARNING: Not enough data for the training
Phase 6: Checking that all the words in the transcript are in the dictionary
Words in dictionary: 11
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
('Sphinxtrain path:', '/cygdrive/d/sphinx4/sphinxtrain-win32')
('Sphinxtrain binaries path:', '/cygdrive/d/sphinx4/sphinxtrain-win32/bin/Release')
Running the training
after that I saw the log file and there is showing error in sphinx_fe.c.
Log file is as follows:-
INFO: cmd_ln.c(697): Parsing command line:
D:\sphinx4\sphinxtrain-win32\bin\Release\sphinx_fe.exe \
-c /cygdrive/d/sphinx4/hindi_model/etc/hindi_model_test.fileids \
-part 1 \
-npart 1 \
-di /cygdrive/d/sphinx4/hindi_model/wav \
-ei wav \
-do /cygdrive/d/sphinx4/hindi_model/feat \
-eo mfc \
-nist no \
-raw no \
-mswav yes \
-samprate 16000 \
-lowerf 130 \
-upperf 6800 \
-nfilt 25 \
-transform dct \
-lifter 22 \
-ncep 13
Current configuration: [NAME][DEFLT][VALUE]
-alpha 0.97 9.700000e-001
-argfile
-blocksize 2048 2048
-build_outdirs yes yes
-c /cygdrive/d/sphinx4/hindi_model/etc/hindi_model_test.fileids
-cep2spec no no
-di /cygdrive/d/sphinx4/hindi_model/wav
-dither no no
-do /cygdrive/d/sphinx4/hindi_model/feat
-doublebw no no
-ei wav
-eo mfc
-example no no
-frate 100 100
-help no no
-i
-input_endian little little
-lifter 0 22
-logspec no no
-lowerf 133.33334 1.300000e+002
-mach_endian little little
-mswav no yes
-ncep 13 13
-nchans 1 1
-nfft 512 512
-nfilt 40 25
-nist no no
-npart 0 1
-nskip 0 0
-o
-ofmt sphinx sphinx
-part 0 1
-raw no no
-remove_dc no no
-remove_noise yes yes
-remove_silence yes yes
-round_filters yes yes
-runlen -1 -1
-samprate 16000 1.600000e+004
-seed -1 -1
-smoothspec no no
-spec2cep no no
-sph2pipe no no
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 6.800000e+003
-vad_postspeech 50 50
-vad_prespeech 10 10
-vad_threshold 2.0 2.000000e+000
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-whichchan 0 0
-wlen 0.025625 2.562500e-002
ERROR: "sphinx_fe.c", line 1023: Failed to open control file /cygdrive/d/sphinx4/hindi_model/etc/hindi_model_test.fileids: No such file or directory
Mon Dec 14 00:10:17 2015
But actually that file is peresent at that location.
so why it is giving an error??
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
You are trying to use Windows binaries with Cygwin, they are not compatible. You can train on Windows without any Cygwin file paths, you need to specify standard Windows file path.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I am training an acoustic model. I getting error while running following command
python sphinxtrain-win32/scripts/sphinxtrain run
output is as follows :-
MODULE: 000 Computing feature from audio files
Extracting features from segments starting at (part 1 of 1)
This step had 1 ERROR messages and 0 WARNING messages. Please check the log file for details.
Extracting features from segments starting at (part 1 of 1)
This step had 1 ERROR messages and 0 WARNING messages. Please check the log file for details.
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 14 words using 17 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: 0.00234166666666667
WARNING: Not enough data for the training
Phase 6: Checking that all the words in the transcript are in the dictionary
Words in dictionary: 11
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
('Sphinxtrain path:', '/cygdrive/d/sphinx4/sphinxtrain-win32')
('Sphinxtrain binaries path:', '/cygdrive/d/sphinx4/sphinxtrain-win32/bin/Release')
Running the training
after that I saw the log file and there is showing error in sphinx_fe.c.
Log file is as follows:-
INFO: cmd_ln.c(697): Parsing command line:
D:\sphinx4\sphinxtrain-win32\bin\Release\sphinx_fe.exe \
-c /cygdrive/d/sphinx4/hindi_model/etc/hindi_model_test.fileids \
-part 1 \
-npart 1 \
-di /cygdrive/d/sphinx4/hindi_model/wav \
-ei wav \
-do /cygdrive/d/sphinx4/hindi_model/feat \
-eo mfc \
-nist no \
-raw no \
-mswav yes \
-samprate 16000 \
-lowerf 130 \
-upperf 6800 \
-nfilt 25 \
-transform dct \
-lifter 22 \
-ncep 13
Current configuration:
[NAME] [DEFLT] [VALUE]
-alpha 0.97 9.700000e-001
-argfile
-blocksize 2048 2048
-build_outdirs yes yes
-c /cygdrive/d/sphinx4/hindi_model/etc/hindi_model_test.fileids
-cep2spec no no
-di /cygdrive/d/sphinx4/hindi_model/wav
-dither no no
-do /cygdrive/d/sphinx4/hindi_model/feat
-doublebw no no
-ei wav
-eo mfc
-example no no
-frate 100 100
-help no no
-i
-input_endian little little
-lifter 0 22
-logspec no no
-lowerf 133.33334 1.300000e+002
-mach_endian little little
-mswav no yes
-ncep 13 13
-nchans 1 1
-nfft 512 512
-nfilt 40 25
-nist no no
-npart 0 1
-nskip 0 0
-o
-ofmt sphinx sphinx
-part 0 1
-raw no no
-remove_dc no no
-remove_noise yes yes
-remove_silence yes yes
-round_filters yes yes
-runlen -1 -1
-samprate 16000 1.600000e+004
-seed -1 -1
-smoothspec no no
-spec2cep no no
-sph2pipe no no
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 6.800000e+003
-vad_postspeech 50 50
-vad_prespeech 10 10
-vad_threshold 2.0 2.000000e+000
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-whichchan 0 0
-wlen 0.025625 2.562500e-002
ERROR: "sphinx_fe.c", line 1023: Failed to open control file /cygdrive/d/sphinx4/hindi_model/etc/hindi_model_test.fileids: No such file or directory
Mon Dec 14 00:10:17 2015
But actually that file is peresent at that location.
so why it is giving an error??
You are trying to use Windows binaries with Cygwin, they are not compatible. You can train on Windows without any Cygwin file paths, you need to specify standard Windows file path.
I am running this command using cmd not from cygwin. But I have cygwin installed.
error solved after uninstallation of cygwin.