For Reference:
Github Link: GitHub - alisonbma/aiSFX: Representation Learning for the Automatic Indexing of Sound Effects Libraries (ISMIR 2022): Deep audio embeddings pre-trained on UCS & Non-UCS-compliant datasets.
Tutorial Link: Tutorial — aiSFX 0.0.0 documentation
I am running;
Debian 12.5
KDE Plasma X11
Python 3.11.7
Pytorch 2.3
Essentia 2.1b6.dev1110
Below is my addition to inference.py:
return output
path_dirAudio = input(“/home/Debian/Desktop/Audio Test”)
path_dirExport = input(“/home/Debian/Desktop/Audio Test Sorted”)
def main(path_dirAudio, path_dirExport,
I am a sound designer and I’m trying to speed up my processes by utilizing a new python script ‘aiSFX’ for use in a linux based conda environment. (I am completely out of my element and a total noob when using linux terminal and python). Following the installation and tutorial instructions step by step, I am confident all perquisites have been fulfilled. Where I am hitting a wall is the tutorial, I have modified the original inference.py file to include my input directory folder location and output directory folder location. I am not sure if that was necessary or if I am supposed to do the “ import sys
import os
sys.path.insert(0, os.path.abspath(‘…/…/…/src’))
“
However when I try to copy and paste that into my conda environment it says: bash: syntax error near unexpected token `0,’
When I type “python aisfx” in my conda environment, it comes back with: File “/home/Debian/aisfx”, line 4
%%CreationDate: (2024-05-31T18:08:26+00:00)
^
SyntaxError: leading zeros in decimal integer literals are not permitted; use an 0o prefix for octal integers
When I paste “aisfx.inference.main()” into my conda environment it drops down a line with “>” in front instead of (myCondaEnvironmentName) which I don’t know what to type after. I am unsure how to proceed, or if I am even following the tutorial correctly. If any other information is necessary, let me know. Any help is greatly appreciated!