Spaces:
Running
on
A10G
Running
on
A10G
syhw
commited on
Commit
•
984b375
1
Parent(s):
e61b298
Update MODEL_CARD.md
Browse files- MODEL_CARD.md +2 -2
MODEL_CARD.md
CHANGED
@@ -52,7 +52,7 @@ The model was evaluated on the [MusicCaps benchmark](https://www.kaggle.com/data
|
|
52 |
|
53 |
## Training datasets
|
54 |
|
55 |
-
The model was trained using the following sources: the [Meta Music Initiative Sound Collection](https://www.fb.com/sound), [Shutterstock music collection](https://www.shutterstock.com/music) and the [Pond5 music collection](https://www.pond5.com/). See the paper for more details about the training set and corresponding preprocessing.
|
56 |
|
57 |
## Quantitative analysis
|
58 |
|
@@ -62,7 +62,7 @@ More information can be found in the paper [Simple and Controllable Music Genera
|
|
62 |
|
63 |
**Data:** The data sources used to train the model are created by music professionals and covered by legal agreements with the right holders. The model is trained on 20K hours of data, we believe that scaling the model on larger datasets can further improve the performance of the model.
|
64 |
|
65 |
-
**Mitigations:**
|
66 |
|
67 |
**Limitations:**
|
68 |
|
|
|
52 |
|
53 |
## Training datasets
|
54 |
|
55 |
+
The model was trained on licensed data using the following sources: the [Meta Music Initiative Sound Collection](https://www.fb.com/sound), [Shutterstock music collection](https://www.shutterstock.com/music) and the [Pond5 music collection](https://www.pond5.com/). See the paper for more details about the training set and corresponding preprocessing.
|
56 |
|
57 |
## Quantitative analysis
|
58 |
|
|
|
62 |
|
63 |
**Data:** The data sources used to train the model are created by music professionals and covered by legal agreements with the right holders. The model is trained on 20K hours of data, we believe that scaling the model on larger datasets can further improve the performance of the model.
|
64 |
|
65 |
+
**Mitigations:** Vocals have been removed from the data source using corresponding tags, and then using using a state-of-the-art music source separation method, namely using the open source [Hybrid Transformer for Music Source Separation](https://github.com/facebookresearch/demucs) (HT-Demucs).
|
66 |
|
67 |
**Limitations:**
|
68 |
|