Add fumifumi model

model_assets/amitaro/style_vectors.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f04b3d679982f11fd29da6ea27f93af86e5876b93aa4fbf910215ce145513cc9
-size 5248

model_assets/{amitaro → fumifumi}/config.json

@@ -1,14 +1,16 @@
 {
-  "model_name": "amitaro",
   "train": {
     "log_interval": 200,
     "eval_interval": 1000,
     "seed": 42,
     "epochs": 100,
     "learning_rate": 0.0001,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 2,
     "bf16_run": false,
     "fp16_run": false,
     "lr_decay": 0.99996,
@@ -23,13 +25,12 @@
     "freeze_JP_bert": false,
     "freeze_EN_bert": false,
     "freeze_emo": false,
-    "freeze_style": false,
-    "freeze_decoder": false
+    "freeze_style": false
   },
   "data": {
     "use_jp_extra": true,
-    "training_files": "Data\\amitaro\\train.list",
-    "validation_files": "Data\\amitaro\\val.list",
+    "training_files": "Data/fumifumi/train.list",
+    "validation_files": "Data/fumifumi/val.list",
     "max_wav_value": 32768.0,
     "sampling_rate": 44100,
     "filter_length": 2048,
@@ -42,15 +43,11 @@
     "n_speakers": 1,
     "cleaned_text": true,
     "spk2id": {
-      "あみたろ": 0
+      "fumifumi": 0
     },
-    "num_styles": 5,
+    "num_styles": 1,
     "style2id": {
-      "Neutral": 0,
-      "01": 1,
-      "02": 2,
-      "03": 3,
-      "04": 4
+      "Neutral": 0
     }
   },
   "model": {
@@ -67,15 +64,43 @@
     "kernel_size": 3,
     "p_dropout": 0.1,
     "resblock": "1",
-    "resblock_kernel_sizes": [3, 7, 11],
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
     "resblock_dilation_sizes": [
-      [1, 3, 5],
-      [1, 3, 5],
-      [1, 3, 5]
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
     ],
-    "upsample_rates": [8, 8, 2, 2, 2],
     "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16, 16, 8, 2, 2],
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      8,
+      2,
+      2
+    ],
     "n_layers_q": 3,
     "use_spectral_norm": false,
     "gin_channels": 512,
@@ -87,5 +112,6 @@
       "initial_channel": 64
     }
   },
-  "version": "2.5.0-JP-Extra"
-}
+  "version": "2.2-JP-Extra",
+  "model_name": "fumifumi"
+}

model_assets/{amitaro/amitaro.safetensors → fumifumi/fumifumi_e100_s5200.safetensors}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19725d9bfd9d4b4fb17072ed4d40e01f6cf89c22cd83c15e1cccbf3ddf6b81de
+oid sha256:f96cd87610c2416b7a931be18773c08ef9da029f327e9a8e36d6e61ab590a120
 size 251150980

model_assets/{jvnv-F1-jp/jvnv-F1-jp_e160_s14000.safetensors → fumifumi/fumifumi_e20_s1000.safetensors}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90fa6c9444d9235c9ec4db99daf7c5c6a21cc26ca141b4c48455d66a3257d01
+oid sha256:9bc71e307fcc7abf45c4b24982d32f28568da80815b9c41dc7686f4692cbfbd0
 size 251150980

model_assets/{jvnv-F2-jp/jvnv-F2_e166_s20000.safetensors → fumifumi/fumifumi_e39_s2000.safetensors}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6289a6f30bb9795744815b9da764a3c8198b18652d9fddef82fff1e14f0e784
+oid sha256:5e14b1a5f01f0159eba55ad11f2faf14b4bc219c8212b48c4634b0e1cfed28d5
 size 251150980

model_assets/{jvnv-M1-jp/jvnv-M1-jp_e158_s14000.safetensors → fumifumi/fumifumi_e58_s3000.safetensors}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d86765f1fe08dbba74cd06283e96b6941b3f232329fabbba9c30e6edc27887a
+oid sha256:f00e08d475ad528a2e4c653ceb53590a310b63933bf8101aa5f5d1065ce86034
 size 251150980

model_assets/fumifumi/fumifumi_e77_s4000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d45fa456b0e433ecfac0411d846b4b8679124fd8c57d872a0a6cb66e97210a7
+size 251150980

model_assets/fumifumi/fumifumi_e97_s5000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32aa89e08be1d9fef1b5f647e8cbf8d59acbf8ca50c46a42ba1f0fdd96cf932
+size 251150980

model_assets/{jvnv-F2-jp → fumifumi}/style_vectors.npy

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900f8cde3a336d12193fec7b7d8e6c5dc77b3a5d719a9be3f8598389cd88e643
-size 7296
+oid sha256:141636846efc64bb151e24a0c131a8571f6e39a4b7c06587ad2c3719882ccce3
+size 1152

model_assets/jvnv-F1-jp/config.json

@@ -1,92 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 300,
-    "learning_rate": 0.0001,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": true,
-    "fp16_run": false,
-    "lr_decay": 0.99996,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "c_commit": 100,
-    "skip_optimizer": true,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false,
-    "freeze_emo": false,
-    "freeze_style": false
-  },
-  "data": {
-    "use_jp_extra": true,
-    "training_files": "Data/jvnv-F1-jp/train.list",
-    "validation_files": "Data/jvnv-F1-jp/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": 1,
-    "cleaned_text": true,
-    "spk2id": {
-      "jvnv-F1-jp": 0
-    },
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    }
-  },
-  "model": {
-    "use_spk_conditioned_encoder": true,
-    "use_noise_scaled_mas": true,
-    "use_mel_posterior_encoder": false,
-    "use_duration_discriminator": false,
-    "use_wavlm_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": 512,
-    "slm": {
-      "model": "./slm/wavlm-base-plus",
-      "sr": 16000,
-      "hidden": 768,
-      "nlayers": 13,
-      "initial_channel": 64
-    }
-  },
-  "version": "2.0-JP-Extra",
-  "model_name": "jvnv-F1-jp"
-}

model_assets/jvnv-F1-jp/style_vectors.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1f959bb45ed0922efc31ff24e9147253814f42cb1d2d1e2bb10391a9df368489
-size 7296

model_assets/jvnv-F2-jp/config.json

@@ -1,92 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 300,
-    "learning_rate": 0.0001,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": false,
-    "fp16_run": false,
-    "lr_decay": 0.99996,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "c_commit": 100,
-    "skip_optimizer": true,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false,
-    "freeze_emo": false,
-    "freeze_style": false
-  },
-  "data": {
-    "use_jp_extra": true,
-    "training_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/jvnv-F2/train.list",
-    "validation_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/jvnv-F2/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": 1,
-    "cleaned_text": true,
-    "spk2id": {
-      "jvnv-F2-jp": 0
-    },
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    }
-  },
-  "model": {
-    "use_spk_conditioned_encoder": true,
-    "use_noise_scaled_mas": true,
-    "use_mel_posterior_encoder": false,
-    "use_duration_discriminator": false,
-    "use_wavlm_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": 512,
-    "slm": {
-      "model": "./slm/wavlm-base-plus",
-      "sr": 16000,
-      "hidden": 768,
-      "nlayers": 13,
-      "initial_channel": 64
-    }
-  },
-  "version": "2.0-JP-Extra",
-  "model_name": "jvnv-F2-jp"
-}

model_assets/jvnv-M1-jp/config.json

@@ -1,92 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 300,
-    "learning_rate": 0.0001,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": true,
-    "fp16_run": false,
-    "lr_decay": 0.99996,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "c_commit": 100,
-    "skip_optimizer": true,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false,
-    "freeze_emo": false,
-    "freeze_style": false
-  },
-  "data": {
-    "use_jp_extra": true,
-    "training_files": "Data/jvnv-M1-jp/train.list",
-    "validation_files": "Data/jvnv-M1-jp/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": 1,
-    "cleaned_text": true,
-    "spk2id": {
-      "jvnv-M1-jp": 0
-    },
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    }
-  },
-  "model": {
-    "use_spk_conditioned_encoder": true,
-    "use_noise_scaled_mas": true,
-    "use_mel_posterior_encoder": false,
-    "use_duration_discriminator": false,
-    "use_wavlm_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": 512,
-    "slm": {
-      "model": "./slm/wavlm-base-plus",
-      "sr": 16000,
-      "hidden": 768,
-      "nlayers": 13,
-      "initial_channel": 64
-    }
-  },
-  "version": "2.0-JP-Extra",
-  "model_name": "jvnv-M1-jp"
-}

model_assets/jvnv-M1-jp/style_vectors.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a925435e8c1c9efc8fc8e90e690655ab9a7bae00a790892e13e936510d04f05
-size 7296

model_assets/jvnv-M2-jp/config.json

@@ -1,92 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 300,
-    "learning_rate": 0.0001,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": true,
-    "fp16_run": false,
-    "lr_decay": 0.99996,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "c_commit": 100,
-    "skip_optimizer": true,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false,
-    "freeze_emo": false,
-    "freeze_style": false
-  },
-  "data": {
-    "use_jp_extra": true,
-    "training_files": "Data/jvnv-M2-jp/train.list",
-    "validation_files": "Data/jvnv-M2-jp/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": 1,
-    "cleaned_text": true,
-    "spk2id": {
-      "jvnv-M2-jp": 0
-    },
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    }
-  },
-  "model": {
-    "use_spk_conditioned_encoder": true,
-    "use_noise_scaled_mas": true,
-    "use_mel_posterior_encoder": false,
-    "use_duration_discriminator": false,
-    "use_wavlm_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": 512,
-    "slm": {
-      "model": "./slm/wavlm-base-plus",
-      "sr": 16000,
-      "hidden": 768,
-      "nlayers": 13,
-      "initial_channel": 64
-    }
-  },
-  "version": "2.0-JP-Extra",
-  "model_name": "jvnv-M2-jp"
-}

model_assets/jvnv-M2-jp/jvnv-M2-jp_e159_s17000.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8245f39438076d36a3befd8aefb15c38830cef326c1f7c9d9c8e64b647645402
-size 251150980

model_assets/jvnv-M2-jp/style_vectors.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c965bb63fa4a759d41a8a4a3649333125d6497ae8a705d81b7d5c5bd2854797c
-size 7296

model_assets/koharune-ami/config.json

@@ -1,92 +0,0 @@
-{
-  "model_name": "小春音アミ",
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 300,
-    "learning_rate": 0.0001,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": false,
-    "fp16_run": false,
-    "lr_decay": 0.99996,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "c_commit": 100,
-    "skip_optimizer": false,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false,
-    "freeze_emo": false,
-    "freeze_style": false,
-    "freeze_decoder": false
-  },
-  "data": {
-    "use_jp_extra": true,
-    "training_files": "Data\\amitaro_combined\\train.list",
-    "validation_files": "Data\\amitaro_combined\\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": 1,
-    "cleaned_text": true,
-    "spk2id": {
-      "小春音アミ": 0
-    },
-    "num_styles": 6,
-    "style2id": {
-      "Neutral": 0,
-      "るんるん": 1,
-      "ささやきA（無声）": 2,
-      "ささやきB（有声）": 3,
-      "ノーマル": 4,
-      "よふかし": 5
-    }
-  },
-  "model": {
-    "use_spk_conditioned_encoder": true,
-    "use_noise_scaled_mas": true,
-    "use_mel_posterior_encoder": false,
-    "use_duration_discriminator": false,
-    "use_wavlm_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": 512,
-    "slm": {
-      "model": "./slm/wavlm-base-plus",
-      "sr": 16000,
-      "hidden": 768,
-      "nlayers": 13,
-      "initial_channel": 64
-    }
-  },
-  "version": "2.5.0-JP-Extra"
-}

model_assets/koharune-ami/koharune-ami.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:980119e6660fc241b1c297016933f43240b3fc6203a9f511dd2f2dac74042991
-size 251150980

model_assets/koharune-ami/style_vectors.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:867527952ff45b6621fe18b8b51728c29abe3aeb80b74e06f235df71aa82ae5d
-size 6272