training sphinx on fedora 9

[vijayabharadwaj gsr]

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 152 words using 36 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.
Total Hours Training: 2.20262179487179
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: 149
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
MODULE: 01 Vector Quantization
Skipped for continuous models
MODULE: 02 Training Context Independent models for forced alignment
Phase 1: Cleaning up directories:
accumulator...logs...qmanager...models...
Phase 2: Flat initialize
[100] FATAL_ERROR: "corpus.c", line 262: input string too long. Truncated.
Something failed: (/home/bharadwaj/sphinx/rm150/scripts_pl/02.falign_ci_hmm/slave_convg.pl)

THis is the error i am getting when i am training sphinx on linux fedora 9, please help

[vijayabharadwaj gsr]

Dear Sir

         I resolved the problem. It's working fantastic on linux.

I have one more question for you. While on linux, windows Xp decoding is very fast, on windows vista it is dead slow. I have build all the sphinx files using visual studio 2008.

Can you give me any suggestion

[David Huggins-Daines]

Hi! Either your file list or your transcript is missing a newline at the end of the file.

Not sure if this is a bug in SphinxTrain or a bug in Emacs :) No, it's a bug in SphinxTrain. But adding the missing newline should fix it.

[vijayabharadwaj gsr]

Dear Sir,

Thanks for replying. If I add a new line, I am getting this error.

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 152 words using 37 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.
Total Hours Training: 2.20328290598291
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: 149
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
WARNING: This phone (c) occurs in the phonelist (/home/bharadwaj/sphinx/150/etc/150.phone), but not in any word in the transcription (/home/bharadwaj/sphinx/150/etc/150_train.transcription)
MODULE: 01 Vector Quantization
Skipped for continuous models
MODULE: 02 Training Context Independent models for forced alignment
Skipped: $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
MODULE: 03 Force-aligning transcripts
Skipped: $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
MODULE: 05 Train LDA transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 06 Train MLLT transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
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%
WARNING: This step had 0 ERROR messages and 2 WARNING messages. Please check the log file for details.
Only 0 parts of 1 of Baum Welch were successfully completed
Parts 1 failed to run!
Training failed in iteration 1
Something failed: (/home/bharadwaj/sphinx/150/scripts_pl/20.ci_hmm/slave_convg.pl)

[Nickolay V. Shmyrev]

At least remove phone (c) from phonelist, see the warning:

WARNING: This phone (c) occurs in the phonelist (/home/bharadwaj/sphinx/150/etc/150.phone), but not in any word in the transcription (/home/bharadwaj/sphinx/150/etc/150_train.transcription)

for more help upload all training folder somewhere and give a link.