feat: added charlotte-jp
Browse files
README.md
CHANGED
@@ -26,7 +26,7 @@ Model Created by ArkanDash <br />
|
|
26 |
The voice that was used in this model belongs to Hoyoverse.
|
27 |
|
28 |
The voice I make to make this model was ripped from the game (3.7). <br />
|
29 |
-
Total Models:
|
30 |
|
31 |
### V1 Model <br />
|
32 |
This was trained on Original RVC.<br />
|
@@ -34,8 +34,7 @@ Pitch Extract using Harvest.<br />
|
|
34 |
This model was trained with 100 epochs, 10 batch sizes, and a 40K sample rate (some models had a 48k sample rate).<br />
|
35 |
Every V1 model was trained more or less around 30 minutes of character voice.
|
36 |
|
37 |
-
I may exclude some models to higher epochs due to the low duration of the character's voice
|
38 |
-
|
39 |
- Klee 150 Epochs
|
40 |
- Fischl 150 Epochs
|
41 |
|
@@ -45,5 +44,6 @@ Pitch Extract using Crepe.<br />
|
|
45 |
This model was trained with 100 epochs, 8 batch sizes, and a 48K sample rate. (some models had a 40k sample rate).<br />
|
46 |
Every V2 model was trained more or less around 60 minutes of character voice.
|
47 |
|
48 |
-
Other request
|
49 |
-
- Greater Lord Rukkhadevata: 750 Epochs, 16 Batch size, 48k Sample rate.
|
|
|
|
26 |
The voice that was used in this model belongs to Hoyoverse.
|
27 |
|
28 |
The voice I make to make this model was ripped from the game (3.7). <br />
|
29 |
+
Total Models: 25 Models (19 V1 Models & 6 V2 Models)
|
30 |
|
31 |
### V1 Model <br />
|
32 |
This was trained on Original RVC.<br />
|
|
|
34 |
This model was trained with 100 epochs, 10 batch sizes, and a 40K sample rate (some models had a 48k sample rate).<br />
|
35 |
Every V1 model was trained more or less around 30 minutes of character voice.
|
36 |
|
37 |
+
I may exclude some models to higher epochs due to the low duration of the character's voice.<br />
|
|
|
38 |
- Klee 150 Epochs
|
39 |
- Fischl 150 Epochs
|
40 |
|
|
|
44 |
This model was trained with 100 epochs, 8 batch sizes, and a 48K sample rate. (some models had a 40k sample rate).<br />
|
45 |
Every V2 model was trained more or less around 60 minutes of character voice.
|
46 |
|
47 |
+
Other request:<br />
|
48 |
+
- Greater Lord Rukkhadevata: 750 Epochs, 16 Batch size, 48k Sample rate. (10 minutes dataset)
|
49 |
+
- Charlotte: 400 Epochs, 16 Batch size, 48k Sample rate. (18 minutes dataset)
|
models/charlotte-jp/added_IVF1318_Flat_nprobe_1_charlotte-jp_v2_400.index
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d18fb9a5a38bba0440a740bc3b9c997dffc0d4d0d97a24cd76293ef9d48ee855
|
3 |
+
size 162414699
|
models/charlotte-jp/charlotte-jp.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53fa283c1066d6cb0672ac753868941c3a0f1095412f0b65daf84c7bb7c90087
|
3 |
+
size 57590442
|
models/charlotte-jp/cover.jpg
ADDED
prezipped/v2/charlotte-jp 400 epochs 48k v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:769a74968231a334ba7f6dda938d5fda5d4088bd9c2c14df8e3484e2e76a9e14
|
3 |
+
size 150159755
|