I followed the training method again as given in
file:///home/shanti/Desktop/April%206/March-29/March24/from%20desktop/March16/Training-testing-sphinx/Training%20Acoustic%20Model%20For%20CMUSphinx%20%5BCMUSphinx%20Wiki%5D.html
I extracted the an4 after installing Sphinxbase and Sphinstrain. Set the paths as suggested.
I get the error when the run the command below:
sphinxtrain run
The Error looks like
ERROR: This step had 638 ERROR messages and 0 WARNING messages. Please check the log file for details. Normalization for iteration: 2 Current Overall Likelihood Per Frame = -152.667054446414 Convergence Ratio = 0.542293305129107 Baum welch starting for 8 Gaussian(s), iteration: 3 (1 of 1) 0% 10% 20% 30% 40% 50% 60% Inside the log file it has the following: ERROR: "backward.c", line 421: Failed to align audio to trancript: final state of the search is not reached ERROR: "baum_welch.c", line 324: TRAIN_DR1_FVFB0_SX312 ignored
Ther error got ignored and and training gets done. How do I solve this to get properly trained model.
This issue is answered in troubleshooting section of model training tutorial
http://cmusphinx.sourceforge.net/wiki/tutorialam#troubleshooting
Thank you very much Nickolay
Log in to post a comment.
I followed the training method again as given in
file:///home/shanti/Desktop/April%206/March-29/March24/from%20desktop/March16/Training-testing-sphinx/Training%20Acoustic%20Model%20For%20CMUSphinx%20%5BCMUSphinx%20Wiki%5D.html
I extracted the an4 after installing Sphinxbase and Sphinstrain.
Set the paths as suggested.
I get the error when the run the command below:
The Error looks like
Ther error got ignored and and training gets done.
How do I solve this to get properly trained model.
Last edit: Nickolay V. Shmyrev 2016-04-07
This issue is answered in troubleshooting section of model training tutorial
http://cmusphinx.sourceforge.net/wiki/tutorialam#troubleshooting
Thank you very much Nickolay