nsynth_wavenet
nsynth_wavenet copied to clipboard
The waveform generated by parallel wavenet looks like the result of the teacher, but quiet noisy.
teacher waveform
student waveform
teacher spectrogram
student spectrogram
The student is run with weight normalization and the default configurations in the parallel_wavenet.json. The wave generated by the student is still quiet noisy. I am testing data dependent initialization fro weight normalization.
Nice. How is the f0 looks like?
hi @bfs18 ! Nice. How many steps have been trained to get that results?
@maozhiqiang The above result is evaluated at 50k steps. I also generate waves at 150k steps. It is a bit clearer, but still noisy.
@bfs18 how about the teacher network's performance? the good teacher network is very very important!
https://github.com/bfs18/nsynth_wavenet/blob/data_dep_init/tests/pred_data-pwn-failed_cases/gen_LJ001-0001-stft_abs.wav I got a bit clearer waveform. @zhang-jian @maozhiqiang
Just wondering if you have tried to train the student model on KL loss only?
@zhang-jian I tried that, but didn't get meaningful result. Experimenting on KL + power loss is more promising. Besides I have limited computing resource. I didn't spent much time on it.
Hi @bfs18 , How many iterations does the teacher network take to get a result like tests/pred_data-use_mu_law+mol/gen_LJ001-0001.wav ?
HI @HallidayReadyOne 200K steps.