Skip to content

Latest commit

 

History

14 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Scripts to experiment with four open-weights text-to-audio models:

Each model needs to be installed and run a bit differently, and in separate Python venvs due to conflicting dependencies. See linux_install.md or macos_install.md. Running on MacOS in particular needs a few patches and workarounds.

Once installed, there are three scripts for each model:

  • *_single.py: generates N samples for a single prompt (both the prompt and N can be set inside the script)
  • *_esc50.py: Re-runs the ESC-50 experiments from our paper, i.e. 100 samples each for the prompt "Sound of [label]" for each label in ESC-50. Note: generates 5000 audio files and will take a while!
  • *_param_count.py: Counts the number of parameters in each model. Added because I got frustrated trying to figure out how big the models were from their papers/documentation.

Our initial paper:

About

Experiments with open-weights text-to-audio models

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages