Heinrich Dinkel commited on
Commit ·
ae36747
1
Parent(s): 199fd5f
Updated
Browse files- .gitattributes +1 -0
- README.md +1 -0
- figures/framework.png +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
figures/framework.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -13,6 +13,7 @@ DashengTokenizer is a high-performance continious audio tokenizer designed for a
|
|
| 13 |
Compared to previous works, our framework simply trains a single linear layer to enable audio generation for semantically strong encoders.
|
| 14 |
|
| 15 |
|
|
|
|
| 16 |
|
| 17 |
|
| 18 |
# Results
|
|
|
|
| 13 |
Compared to previous works, our framework simply trains a single linear layer to enable audio generation for semantically strong encoders.
|
| 14 |
|
| 15 |
|
| 16 |
+
|
| 17 |
|
| 18 |
|
| 19 |
# Results
|
figures/framework.png
ADDED
|
Git LFS Details
|