Commit
•
59fb133
1
Parent(s):
2ef614a
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
The AV_MossFormer2_TSE_16K model weights for 16 kHz audio-visual target speaker extraction in [ClearerVoice-Studio](https://github.com/modelscope/ClearerVoice-Studio/tree/main) repo.
|
| 6 |
+
|
| 7 |
+
This model is trained on large scale open-sourced datasets.
|
| 8 |
+
|
| 9 |
+
It extracts each speaker's voice from a multi-speaker video using facial recognition.
|