Run ../SphinxTrain/scripts.pl/setup_SphinxTrain -update -task name -> OK, no error all file sph are converted in mfc
Run ./scripts.pl/make_feats.pl -ctl etc/name_train.fileids -> OK, no error.
Run ./scripts.pl/RunAll.pl ->
Phase 3: CTL - Check general format; utterance length (must be positive); files exist
Phase 4: CTL - Checking number of lines in the transcript should match lines in control file
Phase 5: CTL - Determine amount of training data, see if n_tied_states seems reasonable.
Estimated Total Hours Training: 0.0476277777777778
This is a small amount of data, no comment at this time
Phase 6: TRANSCRIPT - Checking that all the words in the transcript are in the dictionary
Words in dictionary: 440104
Words in filler dictionary: 3 [b]Use of uninitialized value $_[0] in substitution (s///) at /usr/share/perl/5.12/File/Basename.pm line 341[/b], <trn> line 32.
fileparse(): need a valid pathname at /home/intilinux/Documents/SphinxsAll/Stable/folder/scripts_pl/00.verify/verify_all.pl line 389
Something failed: (/home/intilinux/Documents/SphinxsAll/Stable/folder/scripts_pl/00.verify/verify_all.pl)</trn>
how can I fix this?
Thank you!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Fix the contents of the etc/your_db.fileids file in your training folder. They
should list path to audio files without extension. The number of lines in
fileids file should be exactly the same as the number of lines in
transcription file.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Anonymous
-
2012-01-11
Yes, i resolve the warning message : "WARNING: CTL file missing a newline at
end of file" but :
MODULE: 00 verify training files
O.S. is case sensitive ("A" != "a").
Phones will be treated as case sensitive.
Phase 1: DICT - Checking to see if the dict and filler dict agrees with the
phonelist file.
Found 440107 words using 40 phones
Phase 2: DICT - Checking to make sure there are not duplicate entries in the
dictionary
Phase 3: CTL - Check general format; utterance length (must be positive);
files exist
Phase 4: CTL - Checking number of lines in the transcript should match lines
in control file
Phase 5: CTL - Determine amount of training data, see if n_tied_states seems
reasonable.
Estimated Total Hours Training: 0.0507555555555556
This is a small amount of data, no comment at this time
Phase 6: TRANSCRIPT - Checking that all the words in the transcript are in the
dictionary
Words in dictionary: 440104
Words in filler dictionary: 3
Phase 7: TRANSCRIPT - Checking that all the phones in the transcript are in
the phonelist, and all phones in the phonelist appear at least once Something failed: (/home/.... /scripts_pl/00.verify/verify_all.pl)
Thank you!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I am creating a new model language :
Run ./scripts.pl/RunAll.pl ->
Phase 3: CTL - Check general format; utterance length (must be positive); files exist
Phase 4: CTL - Checking number of lines in the transcript should match lines in control file
Phase 5: CTL - Determine amount of training data, see if n_tied_states seems reasonable.
Estimated Total Hours Training: 0.0476277777777778
This is a small amount of data, no comment at this time
Phase 6: TRANSCRIPT - Checking that all the words in the transcript are in the dictionary
Words in dictionary: 440104
Words in filler dictionary: 3
[b]Use of uninitialized value $_[0] in substitution (s///) at /usr/share/perl/5.12/File/Basename.pm line 341[/b], <trn> line 32.
fileparse(): need a valid pathname at /home/intilinux/Documents/SphinxsAll/Stable/folder/scripts_pl/00.verify/verify_all.pl line 389
Something failed: (/home/intilinux/Documents/SphinxsAll/Stable/folder/scripts_pl/00.verify/verify_all.pl)</trn>
how can I fix this?
Thank you!
Fix the contents of the etc/your_db.fileids file in your training folder. They
should list path to audio files without extension. The number of lines in
fileids file should be exactly the same as the number of lines in
transcription file.
Ok, thank you but hane another error :
how can I fix this?
Something failed: (/home/intilinux/Documents/SphinxsAll ..
/scripts_pl/00.verify/verify_all.pl)
All the phases are no errors ....
There was error. You just need to read carefully.
Yes, i resolve the warning message : "WARNING: CTL file missing a newline at
end of file" but :
MODULE: 00 verify training files
O.S. is case sensitive ("A" != "a").
Phones will be treated as case sensitive.
Phase 1: DICT - Checking to see if the dict and filler dict agrees with the
phonelist file.
Found 440107 words using 40 phones
Phase 2: DICT - Checking to make sure there are not duplicate entries in the
dictionary
Phase 3: CTL - Check general format; utterance length (must be positive);
files exist
Phase 4: CTL - Checking number of lines in the transcript should match lines
in control file
Phase 5: CTL - Determine amount of training data, see if n_tied_states seems
reasonable.
Estimated Total Hours Training: 0.0507555555555556
This is a small amount of data, no comment at this time
Phase 6: TRANSCRIPT - Checking that all the words in the transcript are in the
dictionary
Words in dictionary: 440104
Words in filler dictionary: 3
Phase 7: TRANSCRIPT - Checking that all the phones in the transcript are in
the phonelist, and all phones in the phonelist appear at least once
Something failed: (/home/.... /scripts_pl/00.verify/verify_all.pl)
Thank you!
It might depend on the version you are using. Which sphinxtrain version are
you trying?