Equivalent language model to the web service LM tool

Speech Recognition Toolkit

Brought to you by: air, arthchan2003, awb, bhiksha, and 5 others

This project can now be found here.

Equivalent language model to the web service LM tool

Forum: Help

Creator: Tania Mendonca

Created: 2017-04-12

Updated: 2017-04-12

Tania Mendonca - 2017-04-12

how to form the LM equivalent to the web service LM tool using the SRILM toolkit or CMU SLM kit?

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2017-04-12
  
  Duplicate of https://sourceforge.net/p/cmusphinx/discussion/help/thread/00d0f5f7/?limit=25#8a7e/
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
  - Tania Mendonca - 2017-04-12
    
    Thanks.
    I tried using the perl script but it takes alot of time to form the LM
    So could CMU SLM kit form the LM in faster way when compared to the perl script?
    
    If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Tania Mendonca - 2017-04-12

I did try the CMU SLM toolkit with -absolute parameter my error increased by 2%. How can i achieve the LM same as online LM tool?
the perl script cant handle 2300 sentences to form the LM, its very slow
Please help

Last edit: Tania Mendonca 2017-04-12

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2017-04-13
  
  It is hard to help you with parameters without seeing the data in question and the models.
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Log in to post a comment.