ArkanDash commited on
Commit
985ecd1
1 Parent(s): 562988f

fix: kaveh-jp

Browse files
Files changed (2) hide show
  1. README.md +13 -13
  2. models/model_info.json +2 -2
README.md CHANGED
@@ -18,22 +18,22 @@ Learn more about Retrieval based Voice Conversion in this link below: <br />
18
  # How to use?
19
  Use [Google Colab](https://colab.research.google.com/drive/1vhLofmChcEjjkn8LPf2jkv6Ek5i42wIy?usp=sharing) Or [RVC Models New](https://huggingface.co/spaces/ArkanDash/rvc-models-new) (Which is basically the same but hosted on spaces)
20
 
21
- ## INFO
22
- The voice I make to make this model was ripped from the game (3.7). <br />
23
- Total Models: 20 Models (19 V1 Models & 1 V2 Models)
24
 
25
- Multi Model Inference had an issue when using v2 Model.
 
26
 
27
- ### V1 Model
28
- This model was trained with 100 epochs, 10 batch sizes, and a 40K sample rate. <br />
29
- Every V1 model was trained more or less around 30 minutes of character voice.
30
 
31
  I may exclude some models to higher epochs due to the low duration of the character's voice.
32
- - Klee 150 Epochs
33
- - Fischl 150 Epochs
34
 
35
- ### (New) V2 Model
36
- This model was trained with 100 epochs, 8 batch sizes, and a 48K sample rate. <br />
37
- Every V2 model was trained more or less around 60 minutes of character voice.
38
 
39
- The voice that was used in this model belongs to Hoyoverse.
 
 
 
18
  # How to use?
19
  Use [Google Colab](https://colab.research.google.com/drive/1vhLofmChcEjjkn8LPf2jkv6Ek5i42wIy?usp=sharing) Or [RVC Models New](https://huggingface.co/spaces/ArkanDash/rvc-models-new) (Which is basically the same but hosted on spaces)
20
 
21
+ # INFO
22
+ Created by ArkanDash
23
+ The voice that was used in this model belongs to Hoyoverse.
24
 
25
+ The voice I make to make this model was ripped from the game (3.7).
26
+ Total Models: 20 Models (19 V1 Models & 2 V2 Models)
27
 
28
+ V1 Model
29
+ This model was trained with 100 epochs, 10 batch sizes, and a 40K sample rate (some models had a 48k sample rate).
30
+ Every V2 model was trained more or less around 30 minutes of character voice.
31
 
32
  I may exclude some models to higher epochs due to the low duration of the character's voice.
 
 
33
 
34
+ Klee 150 Epochs
35
+ Fischl 150 Epochs
 
36
 
37
+ (New) V2 Model
38
+ This model was trained with 100 epochs, 8 batch sizes, and a 48K sample rate. (some models had a 40k sample rate).
39
+ Every V2 model was trained more or less around 60 minutes of character voice.
models/model_info.json CHANGED
@@ -151,9 +151,9 @@
151
  "feature_retrieval_library": "added_IVF4454_Flat_nprobe_1_itto-jp_v2.index",
152
  "author":"ArkanDash"
153
  },
154
- "Kaveh-jp": {
155
  "enable": true,
156
- "name": "Kaveh-jp",
157
  "title": "Genshin Impact - Kaveh",
158
  "cover": "cover.png",
159
  "feature_retrieval_library": "added_IVF4967_Flat_nprobe_1_kaveh-jp_v2.index",
 
151
  "feature_retrieval_library": "added_IVF4454_Flat_nprobe_1_itto-jp_v2.index",
152
  "author":"ArkanDash"
153
  },
154
+ "kaveh-jp": {
155
  "enable": true,
156
+ "name": "kaveh-jp",
157
  "title": "Genshin Impact - Kaveh",
158
  "cover": "cover.png",
159
  "feature_retrieval_library": "added_IVF4967_Flat_nprobe_1_kaveh-jp_v2.index",