I have the release version of sphinx 2.06.
I have uploaded my list of words to the LM tool and it generated the various dictionary & vocab files.
I implemented those and the sample continuous app is successful in recognising about half of the words (65 in total).
I am trying to write a sample app that simply detects any of those words in any combination and prints them on screen (I will add this to the main software project later).
Can anyone tell me how to:
1) improve accuracy (If I have to use the trainer for this, how do I replace an4/rm1 with my lm files?)
2) include engine in a C file. Should I just copy sample app & go from there?
I would use the documentation on the CMU site, but it might as well be in hieroglyphics!!!
Thanks for any help!!!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I have the release version of sphinx 2.06.
I have uploaded my list of words to the LM tool and it generated the various dictionary & vocab files.
I implemented those and the sample continuous app is successful in recognising about half of the words (65 in total).
I am trying to write a sample app that simply detects any of those words in any combination and prints them on screen (I will add this to the main software project later).
Can anyone tell me how to:
1) improve accuracy (If I have to use the trainer for this, how do I replace an4/rm1 with my lm files?)
2) include engine in a C file. Should I just copy sample app & go from there?
I would use the documentation on the CMU site, but it might as well be in hieroglyphics!!!
Thanks for any help!!!