Commit
•
ac5df2d
1
Parent(s):
77310d1
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,3 +31,9 @@ For an example of how to use the VALL-E Korean model, you can refer to the provi
|
|
| 31 |
- [Vocos](https://github.com/charactr-platform/vocos)
|
| 32 |
|
| 33 |
For more information and details on using the model, please refer to the provided references and resources.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
- [Vocos](https://github.com/charactr-platform/vocos)
|
| 32 |
|
| 33 |
For more information and details on using the model, please refer to the provided references and resources.
|
| 34 |
+
|
| 35 |
+
# Updated
|
| 36 |
+
|
| 37 |
+
We trained the model on 8k dataset from [AI Hub](https://www.aihub.or.kr), which is uploaded as v1.
|
| 38 |
+
The model has better performance when the clean audio source (e.g., voice-source), however, it may not work well when the audio source is bad.
|
| 39 |
+
Therefore, the both v0 and v1 are maintained.
|