hello,
I have built acoustic model using SphinxTrain and Language Model using "the CMU Cambridge statistical language modeling tool kit v2". Inorder to build the LM I have followed the steps in the typical usage diagram(until the a.binlm generation).
While giving this LM to run "livepretend" of Sphinx3 decoder I am getting an error like :
Bad magic number .....some number here..(4ace...) Not an LM dumpfile.
Please help to solve the problem.
ThanQ.
G Sreenu
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Anonymous
-
2004-06-01
You need to use a util in that comes with sphinx 2 to create the binary dmp file...
it shows up here \sphinx2-0.4\sphinx2-0.4\win32\msdev\SphinxExamples\lm3g2dmp
this should solve your problem
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
hello,
I have built acoustic model using SphinxTrain and Language Model using "the CMU Cambridge statistical language modeling tool kit v2". Inorder to build the LM I have followed the steps in the typical usage diagram(until the a.binlm generation).
While giving this LM to run "livepretend" of Sphinx3 decoder I am getting an error like :
Bad magic number .....some number here..(4ace...) Not an LM dumpfile.
Please help to solve the problem.
ThanQ.
G Sreenu
You need to use a util in that comes with sphinx 2 to create the binary dmp file...
it shows up here \sphinx2-0.4\sphinx2-0.4\win32\msdev\SphinxExamples\lm3g2dmp
this should solve your problem