Update README.md
Browse files
README.md
CHANGED
|
@@ -5,18 +5,18 @@ license: mit
|
|
| 5 |
Selection of trained models for the RhythGen project: https://github.com/efraimdahl/RhythGen
|
| 6 |
|
| 7 |
# Models
|
| 8 |
-
• LAS
|
| 9 |
|
| 10 |
-
• LMR2
|
| 11 |
|
| 12 |
-
• LB
|
| 13 |
|
| 14 |
-
• HAS2
|
| 15 |
|
| 16 |
-
• RAS2
|
| 17 |
collection.
|
| 18 |
|
| 19 |
-
• RB
|
| 20 |
|
| 21 |
|
| 22 |
# Base Model
|
|
|
|
| 5 |
Selection of trained models for the RhythGen project: https://github.com/efraimdahl/RhythGen
|
| 6 |
|
| 7 |
# Models
|
| 8 |
+
• **LAS:** In-attention conditioning with syncopation labels on the Lieder dataset.
|
| 9 |
|
| 10 |
+
• **LMR2:** Attention modulation with spectral weight profiles profiles and a learnable scale (initialized at 10) on the Lieder dataset.
|
| 11 |
|
| 12 |
+
• **LB:** Baseline NotaGen (small) model without any conditioning, finetuned on the Lieder dataset.
|
| 13 |
|
| 14 |
+
• **HAS2:** In-attention conditioning with syncopation labels on the RAG-RH dataset.
|
| 15 |
|
| 16 |
+
• **RAS2:** In-attention conditioning with syncopation scores and voice masking on the RAG-
|
| 17 |
collection.
|
| 18 |
|
| 19 |
+
• **RB:** Baseline NotaGen model without any conditioning, finetuned on the RAG-collection.
|
| 20 |
|
| 21 |
|
| 22 |
# Base Model
|