search

deepsound-project / samplernn-pytorch

PyTorch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
MIT License
288 stars 75 forks source link

Successful implementations? #31

Open Stafla opened 6 years ago

Stafla commented 6 years ago

Hi,

Is there anyone who successfully generated audio using this implementation of SampleRNN? If so, what parameter set did you use? What was your final training and validation loss? Furthermore, did you adjust any code in order to produce audio of good quality?

I ran several instances of this implementation to learn pattern in classical music, using different parameters. The lowest training and validation loss I retrieved was 0.72 and 0.86 (NLL in bits), respectively. The corresponding parameter set was equivalent to the optimal music parameters set according to Mehri et al. However, the generated audio files are still noisy. I know there are people who generated qualitative audio files using the original Theano implementation, although their losses were higher. I, therefore, am wondering if there are people who have or had similar issues. Your help is appreciated :).

Kind regards,

Stafla

dmtrs commented 4 years ago

Hey @Stafla, did you managed to run other implementations? If so, how would compare them with this one?

Could you please share audion samples from your tests?