mtg / music-approachability-engagement

Classification of music approachability and engagement

  • Public
  • 21.3K runs
  • CPU
  • GitHub
  • License

Input

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
file

Audio file to process

string
Shift + Return to add a new line

YouTube URL to process (overrides audio input)

string

Regards to the downstream type: 2class, 3class, regression

Default: "regression"

Output

Rendering markdown...

Generated in

Run time and cost

This model costs approximately $0.00030 to run on Replicate, or 3333 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on CPU hardware. Predictions typically complete within 4 seconds.

Readme

Classification of music approachability and engagement

This demo runs transfer learning models to estimate music approachability and engagement using effnet-discogs embeddings. We include three model types, providing different outcome formats: two classes, three classes, and regression with continuous values:

  • two classes: low, and high approachability and engagement.
  • three classes: low, mid, and high approachability and engagement.
  • regression: continuous values of approachability and engagement from 0 (low) to 1 (high).

These classifiers were trained on in-house MTG datasets.

Source models

effnet-discogs is an EfficientNet architecture trained to predict music styles for 400 of the most popular Discogs music styles.

Transfer learning models

Our models consist of single-hidden-layer MLPs trained on the considered embeddings.

License

These models are part of Essentia Models made by MTG-UPF and are publicly available under CC by-nc-sa and commercial license.