m-a-p
/

music2vec-v1

Feature Extraction

Model card Files Files and versions Community

a43992899 commited on Dec 31, 2022

Commit

c5330aa

·

1 Parent(s): cf1155c

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -7,13 +7,13 @@ inference: false
 **Music2Vec** is accepted as 2-page abstract in Late Breaking Demos (LBD) at the ISMIR 2022.
 It is a completely unsupervised model trained on 1000 hour music audios.
 Our model is SOTA-comparable on multiple MIR tasks even under probing settings, while keeping fine-tunable on a single 2080Ti.
 Larger models trained with more data are on the way~
-![Model Architecture](music2vec.png | width=100)
-We release the crop5s version as music2vec-v1.
-![Performance Comparison](music2vec_performance.png | width=100)
 # Model Usage

 **Music2Vec** is accepted as 2-page abstract in Late Breaking Demos (LBD) at the ISMIR 2022.
 It is a completely unsupervised model trained on 1000 hour music audios.
+We release the crop5s version as music2vec-v1.
 Our model is SOTA-comparable on multiple MIR tasks even under probing settings, while keeping fine-tunable on a single 2080Ti.
 Larger models trained with more data are on the way~
+![Model Architecture](music2vec.png)
+![Performance Comparison](music2vec_performance.png)
 # Model Usage