feat: added faruzan-jp

README.md

@@ -26,7 +26,7 @@ Model Created by ArkanDash <br />
 The voice that was used in this model belongs to Hoyoverse.
 
 The voice I make to make this model was ripped from the game (3.7). <br />
-Total Models: 26 Models (19 V1 Models & 7 V2 Models)
+Total Models: 27 Models (19 V1 Models & 8 V2 Models)
 
 ### V1 Model <br />
 This was trained on Original RVC.<br />
@@ -46,4 +46,9 @@ Every V2 model was trained more or less around 60 minutes of character voice.
 
 Other request:<br />
 - Greater Lord Rukkhadevata: 750 Epochs, 16 Batch size, 48k Sample rate. (10 minutes dataset)
-- Charlotte: 400 Epochs, 16 Batch size, 48k Sample rate. (18 minutes dataset)
+- Charlotte: 400 Epochs, 16 Batch size, 48k Sample rate. (18 minutes dataset)
+
+Note:
+- For faruzan, somehow the index file is smaller, But it output a log when training <br />
+Here: <br />
+`Converged (lack of improvement in inertia) at step 1152/48215`

models/faruzan-jp/added_IVF256_Flat_nprobe_1_faruzan-jp_v2.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4875ecdb7a22a8f54ea1fe897edf8b147eb0dfc9372f104b6706e0ab338c14
+size 31588619

models/faruzan-jp/faruzan-jp.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57164f27f40b4566d5d2e801dc6b89fce48c76354ca8af15e9c600901442f795
+size 57589524

models/model_info.json

@@ -135,6 +135,14 @@
 		"feature_retrieval_library": "added_IVF1318_Flat_nprobe_1_charlotte-jp_v2.index",
 		"author":"ArkanDash"
 	},
+	"faruzan-jp": {
+		"enable": true,
+		"model_path": "faruzan-jp.pth",
+        "title": "Genshin Impact - Faruzan",
+        "cover": "cover.png",
+		"feature_retrieval_library": "added_IVF256_Flat_nprobe_1_faruzan-jp_v2.index",
+		"author":"ArkanDash"
+	},
 	"fischl-jp": {
 		"enable": true,
 		"model_path": "fischl-jp.pth",

prezipped/v2/faruzan-jp 100 epochs 48k v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc822f84fc1fe1abaa09b813c1a91a4a200b8d24b6f6a68c7804258fd06b4fd9
+size 81435258