This model was trained on audio data from Freesound (https://freesound.org/) and the FMA dataset (https://github.com/mdeff/fma). Only audio files with a CC0 license were used from Freesound. From the FMA dataset, the entire large subset and a portion of the full dataset were utilized. This model is released under the MIT License.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support