archinetai/audio-diffusion-pytorch issues and pull requests

#84 - Weird spikes in the loss

Issue - State: open - Opened by return-nihil 5 months ago

#83 - RuntimeError: The size of tensor a (91) must match the size of tensor b (90) at non-singleton dimension 2

Issue - State: open - Opened by erikqu 6 months ago

#82 - Unconditional Generation generates noise

Issue - State: open - Opened by reachomk 7 months ago

#81 - RuntimeError: The size of tensor a (37) must match the size of tensor b (36) at non-singleton dimension 2

Issue - State: closed - Opened by heury 9 months ago - 4 comments

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

Issue - State: open - Opened by piobmx 11 months ago - 5 comments

#79 - CUDA OF Memory for 80GB A100 : follow the mousai paper setting of text condition

Issue - State: open - Opened by SuperiorDtj 12 months ago

#78 - What is the structure of encoder in diffusionAE?

Issue - State: closed - Opened by SuperiorDtj 12 months ago - 1 comment

#76 - I have a few questions about 1D-UNet

Issue - State: open - Opened by 0417keito about 1 year ago - 4 comments

#72 - Class-conditional generation

Issue - State: open - Opened by aqibsaeed over 1 year ago - 1 comment

#71 - AssertionError: ClassiferFreeGuidancePlugin requires embedding

Issue - State: open - Opened by gg4u over 1 year ago

#70 - Adding dilation args for use with updated a-unet PR

Pull Request - State: open - Opened by jmoso13 over 1 year ago - 1 comment

#69 - Can the repo be used to process MIDI data？

Issue - State: open - Opened by zsy1987 over 1 year ago

#67 - Future Work - Models

Issue - State: open - Opened by AI-Guru over 1 year ago

#66 - Model architectures from the paper

Issue - State: closed - Opened by AI-Guru over 1 year ago - 5 comments

#65 - Adds custom loss functionality

Pull Request - State: closed - Opened by AI-Guru over 1 year ago

#64 - Languages

Issue - State: closed - Opened by barredo over 1 year ago - 1 comment

#63 - Trained models

Issue - State: open - Opened by aoezis over 1 year ago

#61 - Questions about conditional generation

Issue - State: open - Opened by AI-Guru over 1 year ago - 2 comments

#60 - New Try

Issue - State: closed - Opened by Leezp99 over 1 year ago

#59 - Spectrogram-based diffusion model

Issue - State: closed - Opened by Tinglok over 1 year ago - 2 comments

#56 - Alternative Noises: Offset, Pyramid, Pink

Issue - State: open - Opened by torridgristle over 1 year ago - 2 comments

#55 - Add support to clip predicted samples to the desired range.

Issue - State: open - Opened by Kinyugo over 1 year ago - 2 comments

#53 - What loss function is being used?

Issue - State: closed - Opened by kitchWWW over 1 year ago - 2 comments

#52 - NaN after training for a while

Issue - State: closed - Opened by jameshball over 1 year ago - 10 comments

#51 - could provide a example recipe?

Issue - State: open - Opened by gandolfxu over 1 year ago - 12 comments

#50 - 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?

Issue - State: closed - Opened by emailandxu over 1 year ago - 1 comment

#49 - How to just train condition audio-diffusion without text-condition?

Issue - State: closed - Opened by LeonJoe13 over 1 year ago - 3 comments

#48 - How to use our own background noisy dataset to generate sample?

Issue - State: closed - Opened by haloha123 over 1 year ago - 1 comment

#47 - can not open music examples websit

Issue - State: closed - Opened by Liujingxiu23 over 1 year ago - 2 comments

#46 - How to convert to wav file to listen to result?

Issue - State: closed - Opened by dillfrescott over 1 year ago - 6 comments

#45 - Typo in Paper

Issue - State: closed - Opened by hu-po over 1 year ago - 1 comment

#44 - VRAM requirements?

Issue - State: closed - Opened by illtellyoulater over 1 year ago - 3 comments

#43 - example for Unconditional Generator fails

Issue - State: closed - Opened by MultiTrickFox over 1 year ago - 2 comments

#42 - Fixed SyntaxError due to missing comma in example

Pull Request - State: closed - Opened by Eleiber over 1 year ago

#41 - feat: LinearAttention & TiledAttention for UnetV0

Pull Request - State: closed - Opened by zaptrem over 1 year ago

#40 - Nightly

Pull Request - State: closed - Opened by flavioschneider over 1 year ago

#39 - Support usage with non-audio data e.g spectrograms

Issue - State: closed - Opened by Kinyugo almost 2 years ago - 7 comments

#38 - custom dataset

Issue - State: closed - Opened by lxa9867 almost 2 years ago

#37 - Add Flash Attention

Pull Request - State: closed - Opened by zaptrem almost 2 years ago - 1 comment

#36 - Fix 2-ch AE default encoder & torch.compile error

Pull Request - State: closed - Opened by zaptrem almost 2 years ago

#35 - Exploding loss

Issue - State: closed - Opened by alexrodi almost 2 years ago - 3 comments

#34 - training with conditioning t5

Issue - State: closed - Opened by nikuson almost 2 years ago - 5 comments

#33 - Am I training the model correctly?

Issue - State: closed - Opened by cat-policlot almost 2 years ago - 2 comments

#27 - Pre-trained Weights of AutoEncoder

Issue - State: closed - Opened by JustinYuu almost 2 years ago - 1 comment

#26 - Error Locating Target

Issue - State: closed - Opened by ModeratePrawn almost 2 years ago - 1 comment

GitHub / archinetai/audio-diffusion-pytorch issues and pull requests