Anonymous - 2000-03-13

Is there a way to use multiple language models on one utternace, without writing it to disk. I was going to try to save everything from the audio card to memory and then initialize the cont_ad_init(...) with a function to read from memory. Is this the best way or is there an easier way.

BTW> i will be using the fwdtree pass and not the best path.

thanks