Hi,
I wrote a really long post and looked for some way to include my files, and lost everything. I have been working on this for weeks. I have followed every suggestion I can find to correct this problem. I am using the latest versions of sphinx and WinPython 2.7 on Win7 (supposed to be 64 bit bit but I/m working on 32bit). I have followed your tutorials as well as every other one I can find. Here is the cmd record:
Microsoft Windows [Version 6.1.7601]
Copyright (c) 2009 Microsoft Corporation. All rights reserved.
C:\Users\User>cd c:\sphinx
c:\Sphinx>python C:\sphinx\sphinxtrain\scripts\sphinxtrain run
Sphinxtrain path: C:/sphinx/sphinxtrain
Sphinxtrain binaries path: C:/sphinx/sphinxtrain/bin/Release
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 phoneli
st file.
Found 1097 words using 27 phones
Phase 2: Checking to make sure there are not duplicate entries in the dictio
nary
Phase 3: Check general format for the fileids file; utterance length (must b
e 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 reaso
nable.
Estimated Total Hours Training: 1.88593333333333
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: 1094
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
Phase 1: Cleaning up directories:
accumulator...logs...qmanager...
Phase 2: Flat initialize
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
Phase 3: Forward-Backward
Baum welch starting for LDA, iteration: 1 (1 of 1)
0% FATAL: "main.c", line 1846: initialization failed
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
Failed to start bw
Only 0 parts of 1 of Baum Welch were successfully completed
Parts 1 failed to run!
I would like to provide all my files but can't see a way of attaching them. I can load them up on my website and give you a link tomorrow if it will help. I would be very grateful for any assistance to get over this step.
Thank you, V.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I wrote a really long post and looked for some way to include my files, and lost everything. I have been working on this for weeks. I have followed every suggestion I can find to correct this problem. I am using the latest versions of sphinx and WinPython 2.7 on Win7 (supposed to be 64 bit bit but I/m working on 32bit). I have followed your tutorials as well as every other one I can find. Here is the cmd record:
Microsoft Windows [Version 6.1.7601]
Copyright (c) 2009 Microsoft Corporation. All rights reserved.
C:\Users\User>cd c:\sphinx
c:\Sphinx>python C:\sphinx\sphinxtrain\scripts\sphinxtrain run
Sphinxtrain path: C:/sphinx/sphinxtrain
Sphinxtrain binaries path: C:/sphinx/sphinxtrain/bin/Release
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 phoneli
st file.
Found 1097 words using 27 phones
Phase 2: Checking to make sure there are not duplicate entries in the dictio
nary
Phase 3: Check general format for the fileids file; utterance length (must b
e 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 reaso
nable.
Estimated Total Hours Training: 1.88593333333333
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
, 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
Phase 1: Cleaning up directories:
accumulator...logs...qmanager...
Phase 2: Flat initialize
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
Phase 3: Forward-Backward
Baum welch starting for LDA, iteration: 1 (1 of 1)
0% FATAL: "main.c", line 1846: initialization failed
This step had 1 ERROR messages and 0 WARNING messages. Please check the log fil
e for details.
Failed to start bw
Only 0 parts of 1 of Baum Welch were successfully completed
Parts 1 failed to run!
I would like to provide all my files but can't see a way of attaching them. I can load them up on my website and give you a link tomorrow if it will help. I would be very grateful for any assistance to get over this step.
Thank you, V.
You can share on dropbox and give here a link