Jean-Marc Valin
Jean-Marc Valin
The code itself causes exactly 10 ms delay. Anything else you see comes from your implementation (most likely how you access the soundcard).
Can you explain what you mean?
The demo program works on raw (no header) audio. You probably want to convert that from/to wav. There's a bunch of programs that can do that. I use sox on...
Why would you want it MPL-licensed. You're aware it's currently BSD, right?
@alebzk the pitch estimation code is mostly copied from Opus, so it's quite possible everything in there isn't optimal for rnnoise. The idea as you seem to have guessed is...
See this call: celt_fir5(x_lp, lpc2, x_lp, len>>1, mem); in pitch_downsample.c
@liuanping so you've been able to train a model with my code -- cool! As for loading it, I've had all kinds of problems getting Keras to do that. I'll...
The output is meant to be redirected to a file and saved. The count variable just determines how many training samples are generated
If you make any change to the way the features are computed (which is the case if you change the number of bands), then you need to retrain all the...
The code is C90 and should compile fine on Windows