feat: added wriothesley
Browse files
README.md
CHANGED
@@ -25,10 +25,10 @@ Model Created by ArkanDash<br />
|
|
25 |
The voice that was used in this model belongs to Hoyoverse.<br />
|
26 |
The voice I make to make this model was ripped from the game (3.6 - 4.2).
|
27 |
|
28 |
-
#### Total Models:
|
29 |
-
#### Total Character Model:
|
30 |
V1 Models: 19 <br />
|
31 |
-
V2 Models:
|
32 |
|
33 |
Duplicate model but different version:
|
34 |
- Zhongli, Nahida, Ayaka, Nilou
|
@@ -41,13 +41,13 @@ Note:
|
|
41 |
- For faruzan, somehow the index file is smaller, Might retrain faruzan.
|
42 |
Error message: `Converged (lack of improvement in inertia) at step 1152/48215` <br />
|
43 |
- Furina has only 20 minutes of dataset. (Will update the model in the future when its 1 hour long)
|
|
|
44 |
- New model will be created using v2 training, I'm no longer making v1 model.
|
45 |
|
46 |
Have a request?<br />
|
47 |
I accept genshin character request if you want it.
|
48 |
Other request outside playable character:<br />
|
49 |
- Greater Lord Rukkhadevata: 750 Epochs, 16 Batch size, 48k Sample rate. (10 minutes dataset)
|
50 |
-
- Charlotte: 400 Epochs, 16 Batch size, 48k Sample rate. (18 minutes dataset)
|
51 |
- La Signora: 1k Epochs, 16 Batch size, 48k Sample rate. (8 minutes dataset)
|
52 |
|
53 |
## <center> Model Training Information
|
|
|
25 |
The voice that was used in this model belongs to Hoyoverse.<br />
|
26 |
The voice I make to make this model was ripped from the game (3.6 - 4.2).
|
27 |
|
28 |
+
#### Total Models: 58 Models
|
29 |
+
#### Total Character Model: 54 Models
|
30 |
V1 Models: 19 <br />
|
31 |
+
V2 Models: 39
|
32 |
|
33 |
Duplicate model but different version:
|
34 |
- Zhongli, Nahida, Ayaka, Nilou
|
|
|
41 |
- For faruzan, somehow the index file is smaller, Might retrain faruzan.
|
42 |
Error message: `Converged (lack of improvement in inertia) at step 1152/48215` <br />
|
43 |
- Furina has only 20 minutes of dataset. (Will update the model in the future when its 1 hour long)
|
44 |
+
- Charlotte has only 18 minutes of dataset. (Will update the model in the future when its 1 hour long)
|
45 |
- New model will be created using v2 training, I'm no longer making v1 model.
|
46 |
|
47 |
Have a request?<br />
|
48 |
I accept genshin character request if you want it.
|
49 |
Other request outside playable character:<br />
|
50 |
- Greater Lord Rukkhadevata: 750 Epochs, 16 Batch size, 48k Sample rate. (10 minutes dataset)
|
|
|
51 |
- La Signora: 1k Epochs, 16 Batch size, 48k Sample rate. (8 minutes dataset)
|
52 |
|
53 |
## <center> Model Training Information
|
prezipped/v2/wriothesley-jp 101 epochs 48k v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af3e9c1a0bb8b3dfe80bdb867de0bb1934aa4f8d53fb7212841e900b6467d213
|
3 |
+
size 380635900
|