soroushmehr/sampleRNN_ICLR2017
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
PythonMIT
Issues
- 0
add table with minimum GPU / VRAM requirements, compute times and performance averages
#30 opened by ballerburg9005 - 7
Training falled after 60000 iterations
#26 opened by qiuqiangkong - 0
- 0
Replicating dataset splits?
#28 opened by f90 - 0
creating a dataset
#27 opened by blccskwknd13 - 0
Using My own Dataset and Training versus Generating
#25 opened by JSai23 - 0
Bad amplitude normalization
#24 opened by Cortexelus - 3
StopIteration
#22 opened by mattearnshaw - 1
- 1
preprocessing data
#18 opened by zhang-jian - 1
- 0
Teacher forcing
#21 opened by Cortexelus - 1
speed of generating speech samples
#19 opened by dengyan - 0
- 12
Noise segments
#17 opened by danieleghisi - 9
Pretty amazing results from a training run on classical guitar music (single instrument), at epoch 5 & 7
#13 opened by LinkOne1A - 13
SampleRNN performance
#7 opened by abhilashi - 1
Unable to run on CPU (vs GPU)
#15 opened by LinkOne1A - 4
- 5
To continue test wav?
#11 opened by lukezos - 16
Training on my own voice wav files
#10 opened by LinkOne1A - 1
Example of music generated using mostly default parameters (tier-2), at epoch9 and epoch11
#9 opened by LinkOne1A - 9
- 2
what is flatten mean in your paper?
#5 opened by weixsong - 1
Wavenet parameters
#6 opened by weixsong - 0