Implemented an updated version of HoloESL that includes Risu and Moona.

model_assets/SBV2_HoloESL/SBV2_HoloESL.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131ce1a928a1c57872e9b1b09dccd5a57a097e68a4f16710352de66aced10fac
-size 198769212
+oid sha256:df215c4b3f40265b6c190ad2b497e77194545e74bf48bb1774a9eaf57503606a
+size 198772284

model_assets/SBV2_HoloESL/config.json

@@ -1,109 +1,115 @@
-{
-  "model_name": "SBV2_HoloESL",
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 100,
-    "learning_rate": 0.0002,
-    "betas": [
-      0.8,
-      0.99
-    ],
-    "eps": 1e-09,
-    "batch_size": 4,
-    "bf16_run": true,
-    "lr_decay": 0.99995,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "skip_optimizer": false,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false,
-    "freeze_style": false
-  },
-  "data": {
-    "training_files": "Data/SBV2_HoloESL/train.list",
-    "validation_files": "Data/SBV2_HoloESL/val.list",
-    "max_wav_value": 32768.0,
-    "sampling_rate": 44100,
-    "filter_length": 2048,
-    "hop_length": 512,
-    "win_length": 2048,
-    "n_mel_channels": 128,
-    "mel_fmin": 0.0,
-    "mel_fmax": null,
-    "add_blank": true,
-    "n_speakers": 2,
-    "cleaned_text": true,
-    "num_styles": 4,
-    "style2id": {
-      "Neutral": 0,
-      "Anya": 1,
-      "IofiLoud": 2,
-      "Iofi": 3
-    },
-    "spk2id": {
-      "AnyaMelfissa": 0,
-      "AiraniIofifteen": 1
-    }
-  },
-  "model": {
-    "use_spk_conditioned_encoder": true,
-    "use_noise_scaled_mas": true,
-    "use_mel_posterior_encoder": false,
-    "use_duration_discriminator": true,
-    "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,
-      8,
-      2,
-      2
-    ],
-    "n_layers_q": 3,
-    "use_spectral_norm": false,
-    "gin_channels": 256
-  },
-  "version": "1.3"
+{
+  "model_name": "SBV2_HoloESL",
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 42,
+    "epochs": 100,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 3,
+    "bf16_run": false,
+    "lr_decay": 0.99995,
+    "segment_size": 16384,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "skip_optimizer": false,
+    "freeze_ZH_bert": false,
+    "freeze_JP_bert": false,
+    "freeze_EN_bert": false,
+    "freeze_style": false,
+    "freeze_encoder": false,
+    "freeze_decoder": false
+  },
+  "data": {
+    "use_jp_extra": false,
+    "training_files": "Data\\SBV2_HoloESL\\train.list",
+    "validation_files": "Data\\SBV2_HoloESL\\val.list",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 5,
+    "cleaned_text": true,
+    "num_styles": 5,
+    "style2id": {
+      "Neutral": 0,
+      "Iofi": 1,
+      "Anya": 2,
+      "Moona": 3,
+      "Risu": 4
+    },
+    "spk2id": {
+      "AyundaRisu": 0,
+      "MoonaHoshinova": 1,
+      "AiraniIofifteen": 2,
+      "AnyaMelfissa": 3
+    }
+  },
+  "model": {
+    "use_spk_conditioned_encoder": true,
+    "use_noise_scaled_mas": true,
+    "use_mel_posterior_encoder": false,
+    "use_duration_discriminator": true,
+    "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,
+      8,
+      2,
+      2
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "version": "2.4.1"
 }

model_assets/SBV2_HoloESL/style_vectors.npy

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c78f385ae4471f3273053f962d72c1c69757ef7b8df3f039a069215ae2195e7d
-size 4224
+oid sha256:5ad49c60a1b326a2710586e5806039add9da059d7dfd07d47d6f04d90de6e3a8
+size 6272

voicelist.json

@@ -125,6 +125,24 @@
 	"primarylang": "EN",
     "cover": "nerissa.png"
   },
+  "Risu": {
+    "enable": true,
+    "model_path": "SBV2_HoloESL",
+    "title": "Ayunda Risu",
+	"speakerid": "AyundaRisu",
+	"datasetauthor": "Kit Lemonfoot",
+	"primarylang": "EN",
+    "cover": "risu.png"
+  },
+  "Moona": {
+    "enable": true,
+    "model_path": "SBV2_HoloESL",
+    "title": "Moona Hoshinova",
+	"speakerid": "MoonaHoshinova",
+	"datasetauthor": "Kit Lemonfoot",
+	"primarylang": "EN",
+    "cover": "moona.png"
+  },
   "Iofi": {
     "enable": true,
     "model_path": "SBV2_HoloESL",