Update README.md
Browse files
README.md
CHANGED
|
@@ -138,7 +138,7 @@ The model was trained on licensed data using the following sources: the [Meta Mu
|
|
| 138 |
Below are the objective metrics obtained on MusicCaps with the released model. Note that for the publicly released models, we had all the datasets go through 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), in order to keep only the instrumental part. This explains the difference in objective metrics with the models used in the paper.
|
| 139 |
|
| 140 |
| Model | Frechet Audio Distance | KLD | Text Consistency |
|
| 141 |
-
|
| 142 |
| **facebook/magnet-small-10secs** | 4.22 | 1.11 | 0.28 |
|
| 143 |
| facebook/magnet-medium-10secs | 4.61 | 1.14 | 0.28 |
|
| 144 |
| facebook/magnet-small-30secs | 4.35 | 1.17 | 0.28 |
|
|
|
|
| 138 |
Below are the objective metrics obtained on MusicCaps with the released model. Note that for the publicly released models, we had all the datasets go through 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), in order to keep only the instrumental part. This explains the difference in objective metrics with the models used in the paper.
|
| 139 |
|
| 140 |
| Model | Frechet Audio Distance | KLD | Text Consistency |
|
| 141 |
+
|---|---|---|---|
|
| 142 |
| **facebook/magnet-small-10secs** | 4.22 | 1.11 | 0.28 |
|
| 143 |
| facebook/magnet-medium-10secs | 4.61 | 1.14 | 0.28 |
|
| 144 |
| facebook/magnet-small-30secs | 4.35 | 1.17 | 0.28 |
|