Get a weekly rundown of the latest AI models and research... subscribe!

Effnet Discogs


AI model preview image
The effnet-discogs model is an EfficientNet model that has been trained to classify music styles based on audio inputs. It can assign one of 400 different music styles from the Discogs taxonomy to an audio clip. This model has been efficiently designed to provide accurate and fast music style classification for various applications.

Use cases

One possible use case for the effnet-discogs model is in music recommendation systems. By analyzing the music style of a user's favorite songs or playlists, the model can suggest similar songs or artists that match the user's preferred style. This can enhance the personalization and discovery features of music streaming platforms, helping users discover new music that aligns with their tastes. Another use case is in genre-based music analysis. The effnet-discogs model can be used to automatically classify large music collections into different genres based on their audio content. This can be useful for music libraries, radio stations, or music blogs to organize and categorize their vast collections more efficiently. It can also help music researchers and analysts in studying genre trends and patterns. The effnet-discogs model can also be applied to audio content moderation. By classifying music styles in real-time, online platforms and streaming services can ensure compliance with their content guidelines and filter out inappropriate or unauthorized music. This can help maintain a safe and regulated environment for users. Potential products or practical uses of the effnet-discogs model include a music style recommendation app that suggests songs based on a user's mood or activity, an AI-powered music player that automatically generates playlists based on different music styles, or an audio analysis tool for DJs and music producers to analyze and classify their music libraries. It can also be integrated into smart speakers or virtual assistants to provide music recommendations tailored to the user's preferred style.


Cost per run
Avg run time

Creator Models

Essentia Bpm$?78
Music Arousal Valence$0.00164,660
Music Approachability Engagement$0.0065,440
Music Classifiers$0.009355,075

Similar Models

No similar models found

Try it!

You can use this area to play around with demo applications that incorporate the Effnet Discogs model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameEffnet Discogs

An EfficientNet for music style classification by 400 styles from the Disco...

Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$0.0006
Prediction HardwareCPU
Average Completion Time3 seconds