teticio/audio-diffusion

Issues

• Training for the purpose of Super res + denoising conditioned on artifacted data

  #52 opened 22 days ago by Respaired
  0

• Autoregressive models for Audio generation

  #51 opened a month ago by darshanmakwana412
  1

• Question about Conditional Audio Generation Part

  #50 opened 4 months ago by AlgernonLiu
  2

• Errors running the notebooks in Colab

  #49 opened 4 months ago by DCooper-nz
  1

• Version number for accelerate package used here is outdated. Might need to add correct version to requirements.txt

  #48 opened 7 months ago by slokeshrestha26
  1

• Questions on conditional generations

  #45 opened 8 months ago by RochMollero
  6

• Request ... No GUI ???

  #47 opened 8 months ago by kalle07
  6

• Music generation conditioned on text and music

  #46 opened 10 months ago by favazmuhammed
  2

• WARNING: audio_to_images: No valid audio files were found error!

  #43 opened a year ago by SepticDNB
  3

• Duration of generated audio

  #42 opened a year ago by drizzle0171
  4

• is it possible to use the train_unet.py script as a regular ldm?

  #40 opened a year ago by drimeF0
  2

• whats the difference between 256 and 512 dataset

  #41 opened a year ago by sankar-mukherjee
  1

• [Little Feedback] Thank you! :)

  #39 opened a year ago by FeelTheFonk
  2

• multi-gpu training

  #38 opened 2 years ago by bluer555
  1

• AttributeError: 'AutoencoderKL' object has no attribute 'sample_size'

  #36 opened 2 years ago by AIWithShrey
  3

• High fidelity training?

  #32 opened 2 years ago by dustyatx
  3

• teticio/audio-diffusion-256 is really good

  #37 opened 2 years ago by GODGANG4885
  1

• Can I input audio file then generate image

  #34 opened 2 years ago by newcworld
  2

• Training own music samples?

  #33 opened 2 years ago by timtensor
  1

• Numpy Error

  #35 opened 2 years ago by markstent
  1

• Dataset constriants

  #30 opened 2 years ago by deepak-newzera
  16

• NameError: name 'transformers' is not defined upon running model via Gradio

  #29 opened 2 years ago by cparks1
  2

• Whether the longer music sample is the repetition of a shorted sample?

  #28 opened 2 years ago by gandolfxu
  1

• how does the audio_to_images.py file work?

  #27 opened 2 years ago by ST2-EV
  3

• Increasing input size

  #25 opened 2 years ago by ST2-EV
  4

• Diffusers v0.12 removed the `ema_model.averaged_model` attribute

  #24 opened 2 years ago by shiehn
  1

• diffusers v-0.12.0 causes import issues

  #23 opened 2 years ago by shiehn
  1

• Recommended training hyperparameters for 44.1Khz & 48Khz Samplerate

  #22 opened 2 years ago by moiseshorta
  2

• Ask for the losses of vae

  #20 opened 2 years ago by 980202006
  1

• train_vae.py report error 'gpu' is not a valid DistributedType

  #18 opened 2 years ago by zhangaixi2008
  5

• Starting Point for Dataset

  #17 opened 2 years ago by JousterL
  4

• Question about add_noise

  #15 opened 2 years ago by 980202006
  5

• How to run this scripts in linux?

  #16 opened 2 years ago by manman25
  2

• Training with size 64 works. Training with size 256 does not yield good results.

  #7 opened 2 years ago by AI-Guru
  3

• training notebook

  #14 opened 2 years ago by GeorvityLabs
  26

• Mind if I share?

  #11 opened 2 years ago by corranmac
  1

• Tiny thing but... 0.1 not .1

  #12 opened 2 years ago by twobob
  2

• Diffusion steps 1000.

  #8 opened 2 years ago by AI-Guru
  1

• Too many open files during preprocessing

  #6 opened 2 years ago by AI-Guru
  2

• How long does it take for the model to converge after training?

  #5 opened 2 years ago by 980202006
  1

• do you think this could be used for timbre transfer?

  #4 opened 2 years ago by johndpope
  1

• IndexError: list index out of range

  #3 opened 2 years ago by cobanov
  2

• Couldn't cast because column names don't match

  #2 opened 2 years ago by mattgallivan
  2

• [Question] What's the toll on a local desktop computer?

  #1 opened 2 years ago by LaughterOnWater
  1