teticio/audio-diffusion

update requirements

update version

add datasets>=2.9.0 requirement

Merge pull request #26 from ST2-EV/patch-1

replacing fs for load_from_disk with storage_options

typo

remove deprecated averaged_model

fix for latest version of diffusers

update version

fix imports

remove mel import

Merge pull request #21 from nturusin/fix/train_model_nb_updated_command

Changed 'scripts/train_unconditional.py' to 'scripts/train_unet.py' in training

correction

gpu default

typo

add conditional training

change mel import

delete erroneous cell

fix when save_model_epochs != save_images_epochs

Merge pull request #19 from sniafas/main

install datasets

add missing pathlib import

migrate to diffusers!

temporary patch

update hack

remove unnecessary check

remove mel from args

use github for mel.png

Update README.md

get_sample_rate

fix audio loading

get ready for migration to diffusers

add sample

use new models for now

tidy

update version

sync with latest version of diffusers

%pip install

fix install

add audio_diffusion_pipeline notebook

add requirements for training VAE

release to pypi

make colab friendly

remove requirements-lock.txt as it is out of date

update models in readme

clarification

added latent diffusion to notebook

add colab link to app

update apps to incude latent diffusion