Add the speaker encoder from Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Browse files- I_da/dvector-step250000.pt +3 -0
- I_da/wav2mel.pt +3 -0
I_da/dvector-step250000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca2cec7aa1e74d2aad9d141546a712a08984905b28e70fc10c9534862ddebeaa
|
| 3 |
+
size 5714361
|
I_da/wav2mel.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6d5c3fb563fe1ad4479dbd82665f211f8b62d108313aa6cdb384c7cf0b0a536
|
| 3 |
+
size 55707
|