Skip to content

Visualization of music-text embeddings spaces

Notifications You must be signed in to change notification settings

philtgun/embeddingviz

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

EmbeddigViz

TODO

Env setup

python3.11 -m venv venv  # whichever way you installed python: bin, pyenv, conda, etc.
source venv/bin/activate.fish  # or .bash, .zsh, etc.
pip install --upgrade pip wheel  # upgrade pip and install wheel
make initdev  # install dev dependencies

Environment variables

  • HUGGINGFACE_TOKEN: HuggingFace API token
  • MTGJAMENDO_METADATA_PATH: UI path to the metadata file (including mtg-jamendo-dataset/data/splits/split-0/autotagging_top50tags-test.tsv)
  • MTGJAMENDO_AUDIO_DIR: Process path where the audio files are stored (should contain 00, 01, etc. directories inside)
  • SECONDS_START: 60.0
  • SECONDS_DURATION: 10.0

Run

streamlit run embeddingviz/app.py

Process audio


About

Visualization of music-text embeddings spaces

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published