Should I format the cmudict in anyway before using in the g2p-seq2seq?

Speech Recognition Toolkit

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

This project can now be found here.

Should I format the cmudict in anyway before using in the g2p-seq2seq?

Forum: Help

Creator: Vickie

Created: 2017-02-17

Updated: 2017-02-17

Vickie - 2017-02-17

Hi:

Trying to use the g2p-seq2seq program. Should I format the cmudict.dict to the SPHINX format before using it as input to train in g2p-seq2seq? or does it take care of that? Just to elaborate, do I need to remove stress markers and variant markers and convert spaces between words and phones to tabs?

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2017-02-17
  
  Just to elaborate, do I need to remove stress markers and variant markers
  
  Yes
  
  and convert spaces between words and phones to tabs?
  
  No
  
  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.