Sorry if this is a really stupid question/post again. So I'm having an issue with converting the .lm this file contains: http://files.kde.org/accessibility/Simon/lm/ensemble_cased.tar.bz2 .lm to a .dmp for some reason when I run the .dmp through Sphinx4 it produces capitalized output only no matter whether I have -case lower or -case upper and the words don't really match up either. I've also just tried using the .dmp that is packaged with it without a successful result either. I used Sphinxbase to convert the .lm file with this command: sphinx_lm_convert -i words.lm -o words.dmp as well as trying sphinx_lm_convert -i words.lm -ifmt lm -o words.dmp -ofmt dmp. Neither of which seemed to work.
Anyway thank you for any help you are able to provide, and once again sorry if this is a stupid question.
Last edit: Jack Woolford 2015-05-24
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
Sorry if this is a really stupid question/post again. So I'm having an issue with converting the .lm this file contains: http://files.kde.org/accessibility/Simon/lm/ensemble_cased.tar.bz2 .lm to a .dmp for some reason when I run the .dmp through Sphinx4 it produces capitalized output only no matter whether I have -case lower or -case upper and the words don't really match up either. I've also just tried using the .dmp that is packaged with it without a successful result either. I used Sphinxbase to convert the .lm file with this command: sphinx_lm_convert -i words.lm -o words.dmp as well as trying sphinx_lm_convert -i words.lm -ifmt lm -o words.dmp -ofmt dmp. Neither of which seemed to work.
Anyway thank you for any help you are able to provide, and once again sorry if this is a stupid question.
Last edit: Jack Woolford 2015-05-24
I am not sure what problem do you have, you probably want to explain in more details.
sphinx4 is case sensitive, uppercase and lowercase are handled differently. To convert language model in arpa format to lowercase you can use tr:
You also need to make sure that dictionary is lowercase then.
how do i convert lm file to .dmp, i mean what is the converter for convert the file
https://cmusphinx.github.io/wiki/tutoriallm/#converting-a-model-into-the-binary-format