Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,7 @@ inference: false
|
|
5 |
|
6 |
# Introduction
|
7 |
|
8 |
-
|
9 |
It is a completely unsupervised model trained on 1000 hour music audios.
|
10 |
Our model is SOTA-comparable on multiple MIR tasks even under probing settings, while keeping fine-tunable on a single 2080Ti.
|
11 |
|
@@ -42,7 +42,7 @@ Our model is based on the [data2vec audio model](https://huggingface.co/docs/tra
|
|
42 |
|
43 |
# Citation
|
44 |
|
45 |
-
The paper can be found at [
|
46 |
|
47 |
```shell
|
48 |
to be done
|
|
|
5 |
|
6 |
# Introduction
|
7 |
|
8 |
+
**Music2Vec** is accepted as 2-page abstract in Late Breaking Demos (LBD) at the ISMIR 2022.
|
9 |
It is a completely unsupervised model trained on 1000 hour music audios.
|
10 |
Our model is SOTA-comparable on multiple MIR tasks even under probing settings, while keeping fine-tunable on a single 2080Ti.
|
11 |
|
|
|
42 |
|
43 |
# Citation
|
44 |
|
45 |
+
The paper can be found at [ISMIR](https://ismir2022program.ismir.net/lbd_410.html).
|
46 |
|
47 |
```shell
|
48 |
to be done
|