Hi all,
I am a newbie to the Sphinx.
I have multiple wav files and in each of these wav file, (different) speaker says only a few sentences (20-30 words). I want to train on these wav files and then want to use the models obtained for decoding another set of wav files that have the same words in them. Could anyone please tell me the process for training?
I can see there is wav file demo in Sphinx4 but it is only for digits. What changes I would have to made for decoding the wav file containing sentences?
I will be thankful if any body points to the earlier post if that deals with the same problem.
Thanks,
Rashid
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi all,
I am a newbie to the Sphinx.
I have multiple wav files and in each of these wav file, (different) speaker says only a few sentences (20-30 words). I want to train on these wav files and then want to use the models obtained for decoding another set of wav files that have the same words in them. Could anyone please tell me the process for training?
I can see there is wav file demo in Sphinx4 but it is only for digits. What changes I would have to made for decoding the wav file containing sentences?
I will be thankful if any body points to the earlier post if that deals with the same problem.
Thanks,
Rashid