Hugging Face's logo

Spaces:
teticio
/
audio-diffusion
Runtime error

App Files Community
1
audio-diffusion / scripts /train_vae.py

Commit History

add sample_rate and n_fft params
5bc60f9

teticio commited on

add attribution
f8a240c

teticio commited on

add max_epochs arg
b3e97c5

teticio commited on

add max_epochs arg
a8d2b62

teticio commited on

fix audio logging for VAE
c5dcd04

teticio commited on

move resolution specification to dataset generation
327bccf

teticio commited on

update readme
01c4a98

teticio commited on

get working for monochrome
529c646

teticio commited on

take channels into account
4f552a8

teticio commited on

take channels into account
13aa297

teticio commited on

various fixes
2561128

teticio commited on

fixes
21c77d0

teticio commited on

update readme
d122744

teticio commited on

tidy
001a426

teticio commited on

fix progress bar
399a445

teticio commited on

update train_unconditional for latent diffusion
f15cb42

teticio commited on

update train_unconditional for latent diffusion
8f292f9

teticio commited on

merge with diffusers latest version
9a9737e

teticio commited on

added vae notebook
7aaaf62

teticio commited on

convert to hf model
8aa7c27

teticio commited on