I'm using the latest SphinxTrain CVS. I've setup my model according to tinydoc.txt, and get as far as the ./scripts_pl/02.ci_schmm/slave_convg.pl step.
It runs for a bit, then I get the following error:
Using 1 files: 0% ERROR: 12864 1941 ERROR: "backward.c", line 929: alpha(5.047836e-01) <> sum of alphas * betas (4.996917e-01) in frame 13415ERROR: ERROR: "baum_welch.c", line 279: teacher_in_space ignoredFinished
The bw log is located <A HREF="http://intolerance.digitalpassage.com/misc/nasa.1-1.bw.log">here</A>
What does this mean, or how could I possibly find out?
Thanks,
Stephen
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
It looks like the trainer rejected one utterance. If you look in the training documentation, it says you should expect that up to a few percent of your utterances get rejected.
What's happening (probably) is that your acoustic models don't match the training data for this utterance closely enough, and the Baum-Welch forward-backward computation is failing for that utterance. This can happen due to noise in the data, an unusual pronunciation in the utterance, errors in the pronunciation dictionary, or just bad luck (Gaussian mixture models have their problems).
The system will ignore that one utterance for training, which is
fine. The error really is for diagnostic purposes only. If you find that you are seeing this error for a large fraction of the training utterances, then you can start worrying.
-Carl
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
The documentation says utterances should be less than 100 seconds. Apparently bw doesn't normalize every frame (I can't imagine why) and scores underflow after about 10000 frames. In general long utterances will have an increased probability of rejection.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
The documentation says utterances should be less than 100 seconds. Apparently bw doesn't normalize every frame (I can't imagine why) and scores underflow after about 10000 frames. In general long utterances will have an increased probability of rejection.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I'm using the latest SphinxTrain CVS. I've setup my model according to tinydoc.txt, and get as far as the ./scripts_pl/02.ci_schmm/slave_convg.pl step.
It runs for a bit, then I get the following error:
Using 1 files: 0% ERROR: 12864 1941 ERROR: "backward.c", line 929: alpha(5.047836e-01) <> sum of alphas * betas (4.996917e-01) in frame 13415ERROR: ERROR: "baum_welch.c", line 279: teacher_in_space ignoredFinished
The bw log is located <A HREF="http://intolerance.digitalpassage.com/misc/nasa.1-1.bw.log">here</A>
What does this mean, or how could I possibly find out?
Thanks,
Stephen
Here is the correct url
<A HREF="http://intolerance.digitalpassage.com/misc/nasa.1-1.bw.log">http://intolerance.digitalpassage.com/misc/nasa.1-1.bw.log</A>
It looks like the trainer rejected one utterance. If you look in the training documentation, it says you should expect that up to a few percent of your utterances get rejected.
What's happening (probably) is that your acoustic models don't match the training data for this utterance closely enough, and the Baum-Welch forward-backward computation is failing for that utterance. This can happen due to noise in the data, an unusual pronunciation in the utterance, errors in the pronunciation dictionary, or just bad luck (Gaussian mixture models have their problems).
The system will ignore that one utterance for training, which is
fine. The error really is for diagnostic purposes only. If you find that you are seeing this error for a large fraction of the training utterances, then you can start worrying.
-Carl
Ahh, thanks for the help. How long should my utterences be? This one was about 30 seconds.
The documentation says utterances should be less than 100 seconds. Apparently bw doesn't normalize every frame (I can't imagine why) and scores underflow after about 10000 frames. In general long utterances will have an increased probability of rejection.
The documentation says utterances should be less than 100 seconds. Apparently bw doesn't normalize every frame (I can't imagine why) and scores underflow after about 10000 frames. In general long utterances will have an increased probability of rejection.