Difference between revisions of "Leafaudio"
Jump to navigation
Jump to search
| Line 1: | Line 1: | ||
| − | [[Category:Software]][[Category:Audio]] | + | [[Category:Software]][[Category:Audio]][[Category:Machine Learning]] |
{|<!--CONFIGURATION: REQUIRED--> | {|<!--CONFIGURATION: REQUIRED--> | ||
|{{#vardefine:app|leafaudio}} | |{{#vardefine:app|leafaudio}} | ||
Latest revision as of 19:49, 15 August 2022
Description
LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a very small number of parameters.
Environment Modules
Run module spider leafaudio to find out what environment modules are available for this application.
System Variables
- HPC_LEAFAUDIO_DIR - installation directory
Additional Information
LEAF-Audio requires large tensorflow datasets. Move your ~/tensorflow_datasets directory to your blue storage and create a symlink to the new location to avoid filling up your home quota.