audio-diffusion-pytorch

audio-diffusion-pytorch copied to clipboard

Hi, I'm training on a dataset of songs, and I was training with this package. After about 10 epochs (of 1000 samples each) the loss seems to converge, however after...

reachomk

Unconditional model generates okay quality of fake human voice but failed on music.

4

Hi, I've been playing with this diffusion model library for a few days, it is great to have such library that allows common users to train audio data with limited...

piobmx

Questions about conditional generation

2

Hi! I have worked with unconditional generation using this fine repo. It is a lot of fun! I will do latent diffusion next. I am already looking forward to it....

AI-Guru

the test auido is 32-channel 2**15-length, for the batch 2 Besides, the num of trainable paras of the text condition generationis only 672M when follow the paper setting(text embding dim...

SuperiorDtj

I have a few questions about 1D-UNet

4

The code shows that a-unet is used to construct the unet, but looking at the a-unet, the unet is constructed in a nested-like structure. So, does this unet have middle...

0417keito

Class-conditional generation

1

Hi, Is it possible to do class-conditional generation instead of text-conditioning? Thanks.

aqibsaeed

Adding dilation args for use with updated a-unet PR

1

This PR adds default args to the construction of the UNet to include dilation and dropout. Details on changes to underlying repo for this to work can be found here:...

jmoso13

Hi, I test the example you gave for conditioning on text, but got error: ``` # Train model with audio waveforms audio_wave = torch.randn(1, 2, 2**18) # [batch, in_channels, length]...

gg4u

zsy1987

Hi! I am very curious about the future work part of the paper. There were a few suggestions in the paper. Let me talk about two. ## 1. Use perceptual...

AI-Guru