add hibiki model

README.md

@@ -7,11 +7,12 @@ license: mit
 
 由[so-vits-svc-4.0](https://github.com/innnky/so-vits-svc/tree/4.0)训练的模型 **不是v2**
 
-- [ick](https://pjsekai.sega.jp/character/unite01/ichika/index.html) - 约1500条语音 [source](https://pjsek.ai/assets/ondemand/sound/card_scenario/voice)
-- [saki](https://pjsekai.sega.jp/character/unite01/saki/index.html) - 约1500条语音 [source](https://pjsek.ai/assets/ondemand/sound/card_scenario/voice)
-- [riri](https://bgm.tv/character/76764) - 5k条游戏语音, 包含hs
+- [ick(星乃一歌)](https://pjsekai.sega.jp/character/unite01/ichika/index.html) - 约1500条语音 [source](https://pjsek.ai/assets/ondemand/sound/card_scenario/voice)
+- [saki(天馬咲希)](https://pjsekai.sega.jp/character/unite01/saki/index.html) - 约1500条语音 [source](https://pjsek.ai/assets/ondemand/sound/card_scenario/voice)
+- [riri(鹿島理々)](https://bgm.tv/character/76764) - 约5k条语音, 包含hs语音
     - ![220ep](./assets/riri_220epoch.png)
-- [sora](https://bgm.tv/character/27602) - 游戏语音, 数量忘了, 包含hs
+- [sora(一ノ瀬空)](https://bgm.tv/character/27602) - 约3.5k条语音, 包含hs语音
+- [hibiki(小日向響)](https://bgm.tv/character/76763) - 约7k条语音, 包含hs的语音
 
 
 模型命名遵循`G_${name}_${Epoch}.pth`.

hibiki/G_hibiki_38.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220b1be481d9c9dc4e0d50eef25dfa718522a8b794aa12567c4b8940da182006
+size 542789405

hibiki/config.json

@@ -0,0 +1,93 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 60,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "hibiki": 0
+  }
+}