Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ The training recipe involves a VALL-E approach of giving 400 audio tokens as con
|
|
| 19 |
perform zero-shot voice cloning. This has not been completely accomplished, as the amount of training data is insufficient. However, the model is capable of grasping
|
| 20 |
concepts such as the gender of the voice, producing male voices when given male context and viceversa.
|
| 21 |
|
| 22 |
-
You can visit a demo page with some audios at https://github.
|
| 23 |
|
| 24 |
Training and inference recipes will be published soon.
|
| 25 |
|
|
|
|
| 19 |
perform zero-shot voice cloning. This has not been completely accomplished, as the amount of training data is insufficient. However, the model is capable of grasping
|
| 20 |
concepts such as the gender of the voice, producing male voices when given male context and viceversa.
|
| 21 |
|
| 22 |
+
You can visit a demo page with some audios at https://erikupv.github.io/QWav3_Demo/
|
| 23 |
|
| 24 |
Training and inference recipes will be published soon.
|
| 25 |
|