binary to arpa language model conversion

Speech Recognition Toolkit

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

This project can now be found here.

binary to arpa language model conversion

Forum: Help

Creator: Thomas Pellegrini

Created: 2009-05-12

Updated: 2012-09-22

Thomas Pellegrini - 2009-05-12

Hello,

I successfully ran the Sphinx4 decoder on HUB-4 speech data with the provided language (LM) and acoustic models. I wanted to convert the binary LM to its arpa version. When I load the binary LM (called language_model.arpaformat.DMP), with the CMU LM toolkit function binlm2arpa, I get this error:

Reading binary language model from ../sphinx4/models/language/hub4/language_model.arpaformat.DMP...Error : Language model file ../sphinx4/models/language/hub4/language_model.arpaformat.DMP appears to be corrupted.

When I comment the corresponding test in load_lm.c comparing the LM version with the BBO_FILE_VERSION variable, I get this error:

Reading in language model from file ../sphinx4/models/language/hub4/language_model.arpaformat.DMP
sih_val_rd_fm_file ERROR: version of '../sphinx4/models/language/hub4/language_model.arpaformat.DMP' is 1634889825, current version is 24844

I work on a 64-bit machine:
Linux 2.6.22.17-0.1-default #1 SMP 2008/02/10 20:01:04 UTC x86_64

Thanks in advance for your help,
Best regards,

Thomas

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2009-05-13
  
  Use sphinx3_lm_convert.
  
  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.