# Load model directly
from transformers import AutoProcessor, AutoModel
processor = AutoProcessor.from_pretrained("mbien/fma2vec")
model = AutoModel.from_pretrained("mbien/fma2vec")Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Predicting music popularity using DNNs
This is a pre-trained wav2vec2.0 model, trained on a fill Free Music Archive repository, created as part of DH-401: Digital Musicology class on EPFL
Team
- Elisa (elisa.michelet@epfl.ch)
- Michał (michal.bien@epfl.ch)
- Noé (noe.durandard@epfl.ch)
Milestone 3
Main notebook presenting out results is available here
Notebook describing the details of Wav2Vec2.0 pre-training and fine-tuning for the task is available here
Milestone 2
Exploratory data analysis notebook is available here
Milestone 1
Refined project proposal is available here
Milestone 0
Original project proposal is available in git history here
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="mbien/fma2vec")