Issues
- 10
NaN after training for a while
#52 opened by jameshball - 0
Weird spikes in the loss
#84 opened by return-nihil - 4
RuntimeError: The size of tensor a (37) must match the size of tensor b (36) at non-singleton dimension 2
#81 opened by heury - 0
RuntimeError: The size of tensor a (91) must match the size of tensor b (90) at non-singleton dimension 2
#83 opened by erikqu - 0
Unconditional Generation generates noise
#82 opened by reachomk - 4
Model architectures from the paper
#66 opened by AI-Guru - 4
Unconditional model generates okay quality of fake human voice but failed on music.
#80 opened by piobmx - 2
Questions about conditional generation
#61 opened by AI-Guru - 1
- 0
CUDA OF Memory for 80GB A100 : follow the mousai paper setting of text condition
#79 opened by SuperiorDtj - 4
I have a few questions about 1D-UNet
#76 opened by 0417keito - 1
Class-conditional generation
#72 opened by aqibsaeed - 0
- 0
Can the repo be used to process MIDI data?
#69 opened by zsy1987 - 0
Future Work - Models
#67 opened by AI-Guru - 1
- 0
Trained models
#63 opened by aoezis - 0
- 12
could provide a example recipe?
#51 opened by gandolfxu - 2
- 3
- 2
Spectrogram-based diffusion model
#59 opened by Tinglok - 2
Alternative Noises: Offset, Pyramid, Pink
#56 opened by torridgristle - 2
What loss function is being used?
#53 opened by kitchWWW - 1
- 1
Question: the sigma_t is not samped from 0 to 1 in v-diffusion, which is not like your thesis mentioned, will it cause any trouble?
#50 opened by emailandxu - 3
VRAM requirements?
#44 opened by illtellyoulater - 1
Typo in Paper
#45 opened by hu-po - 6
- 7
- 2
can not open music examples websit
#47 opened by Liujingxiu23 - 2
Am I training the model correctly?
#33 opened by cat-policlot - 2
example for Unconditional Generator fails
#43 opened by MultiTrickFox - 0
custom dataset
#38 opened by lxa9867 - 5
training with conditioning t5
#34 opened by nikuson - 3
Exploding loss
#35 opened by alexrodi - 1
Pre-trained Weights of AutoEncoder
#27 opened by JustinYuu - 1
Error Locating Target
#26 opened by ModeratePrawn - 3
- 2
Using the audio_975 model with colab fails
#21 opened by timohear - 10
Question: Scaling guide/suggested parameters?
#5 opened by zaptrem - 4
Add trainer
#3 opened by nateraw - 4
text conditioned infinite ASMR generator?
#2 opened by lucidrains