«
»

Importing 21007 wav files

At the moment, I am importing 21007 wav files into simon. I want to increase the amount of training data.

import-wav-filesIt takes a few minutes until all files are imported.

I hope that it will work as expected.

Edit: No, it just worked partially. Just about 862 words are contained in the file file:///home/ubuntu/.kde/share/apps/simond/models/default/active/model.dict. Why does simon use just this small subset?

Edit #2: I selected the “static model” option instead of “user generated model”. I will try again.

Edit #3: Obviously, I imported only a small dictionary. This means that the acoustic model has been trained with 21007 words, but the language model contains just 862 words.

Edit #4: I think that I found the mistake. The file file:///home/ubuntu/Documents/201008/lexicon-all.xml doesn’t contain valid XML code. I have to fix that, then I will try again.

This entry was posted on Friday, August 20th, 2010 at 7:04 pm and is filed under Ubuntu. You can follow any responses to this entry through the RSS 2.0 feed. Both comments and pings are currently closed.

One Response to “Importing 21007 wav files”

  1. Peter Grasch says:
    August 20, 2010 at 11:43 pm

    When I build huge models, I usually import your dictionary in the active dictionary (beware this will use a LOT of ram (when synchronizing about 3 GB)) and just let simon figure out the rest.

    Regards,
    Peter