You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have svn up to the latest version. Now, I can sucessfully add model to the
database and undergo voice matching. But, I soon discover some wav file cannot
produce a gmm file when undergoing db.add_model. I guess, is it because of the
sampling rate or anything else that contribute to success or failure despite
the same wav file format of source? Can you tell me what kind of wav file is
likely successful?
Original issue reported on code.google.com by idiscove...@gmail.com on 16 Jul 2012 at 10:55
The text was updated successfully, but these errors were encountered:
Hello, the waves that surely work have these specs "RIFF (little-endian) data,
WAVE audio, Microsoft PCM, 16 bit, mono 16000 Hz". We will try to make the tool
more flexible.
Notice that if you add a model for a speaker already in the db (same name), its
gmm file will be updated and not created another one.
If you want you can send us wave samples that do not work.
If you get any explicit error, please let us know.
Original comment by michelaf...@gmail.com on 16 Jul 2012 at 12:36
I have tried and now they work. Thanks for your reply.
By the way, what kind of video file can be accepted in voiceidplayer gui? I
have downloaded mp4 file from youtube but it doesn't work.=)
Original comment by idiscove...@gmail.com on 18 Jul 2012 at 6:52
I'm glad I was helpful!
For the GUI maybe is an installation issue. The video formats accepted are
those of mplayer. We mostly use mp4 file format. Can you specify the error? So
we can give you a better answer ;)
Original comment by michelaf...@gmail.com on 18 Jul 2012 at 8:13
Original issue reported on code.google.com by
idiscove...@gmail.com
on 16 Jul 2012 at 10:55The text was updated successfully, but these errors were encountered: