m-a-p
/

music2vec-v1

Feature Extraction

Model card Files Files and versions

a43992899 commited on Dec 31, 2022

Commit

cf1155c

·

1 Parent(s): 4e56ec4

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -10,10 +10,10 @@ 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 =250x250)
 We release the crop5s version as music2vec-v1.
-![Performance Comparison](music2vec_performance.png =250x250)
 # Model Usage

 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