Re:WaveNet implementation in Keras
by espadrine on Thursday September 15, 2016 @09:30AM
(#12505939)
Do you have a link?
This implementation says: āA Tesla K80 needs around ~4 minutes for generating a second of audio at a sampling rate of 4000hzā, which is significantly faster.
Re:WaveNet implementation in Keras
by basve on Thursday September 15, 2016 @09:46AM
(#12506044)
90 minutes for 1s of audio was reported by someone from Google on twitter, but the tweet has been deleted.
I've clarified in the readme that my measurements are for a much lighter/smaller model than Deepmind's :).
This implementation says: āA Tesla K80 needs around ~4 minutes for generating a second of audio at a sampling rate of 4000hzā, which is significantly faster.