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

Generation is always the same #14

Closed davidmrdavid closed 6 years ago

davidmrdavid commented 6 years ago

Hello,

I'm running train.py with different datasets and, although the loss decreases differently for each dataset, the generated samples are always exactly the same across different datasets. Is this a known issue?

davidmrdavid commented 6 years ago

It turns out that the issue had to do with caching on my end. Closing the issue