Upload 91 files

AstonMachan/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602610f49a2626c538ade6cb31fb755772a6ecb1b326b903ffc9c1a3a07334d0
+size 158897385

AstonMachan/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "AstonMachan": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

CopanoRickey/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb764d50b75d3b5fe08134a728cdf78a410f39fdbc7a46252509d0dab22b2416
+size 158897385

CopanoRickey/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "CopanoRickey": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

DaiichiRuby/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2d3b8d48c836040a3d201d0a87096b305ed742045228b44f7ba4c9102f672e
+size 158897385

DaiichiRuby/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "DaiichiRuby": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

GoldCity/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a25ae8d604cafbcf437a458e956d18b2e8b5c5da6fbdc76e8b665f0f5d4475
+size 158897385

GoldCity/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "GoldCity": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

HishiMiracle/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40c92a19f32ef53eb9c6327221614a4e0715d1a2a540c81e64f9c2d4accceaf
+size 158897385

HishiMiracle/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "HishiMiracle": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

HokkoTarumae/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a129accba25741cc68df761ac8ce3ddb5e8b9cabe26494ef4bcbce6fc818ccb7
+size 158897385

HokkoTarumae/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "HokkoTarumae": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

InariOne/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752367333841c8bbc9b426f26d00f5c79cf9cbe06811f0e95428d59d593355a6
+size 158897385

InariOne/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "InariOne": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

InesFujin/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439ad85c65f72d20ea6e2df60039bc4e234dc3b9091cd85dd01f78df2fd20e91
+size 158897385

InesFujin/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "InesFujin": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

Maruzensky/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b555dd37d42695c4a09a1a4e3d9fb52badd5c8e0a15f3982fb57a52d21970f9d
+size 158897385

Maruzensky/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "Maruzensky": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

MejiroBright/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f578be56c1deacc84ddb9664e5f08288faf3699ba458a0eecfdb09c3187235d9
+size 158897385

MejiroBright/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "MejiroBright": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

MejiroDober/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426b6e7f3f7570de564a9e31b228757d775d2e031dbf371314c2f6026737477e
+size 158897385

MejiroDober/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "MejiroDober": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

MihonoBourbon/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53dcb87912a6dbfd931710b140cb89b878072a61315fd1be4bfeb174bc0affa2
+size 158897385

MihonoBourbon/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "MihonoBourbon": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

Mr.C.B/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50483df4b0bbc3d7efbf406481a19457dfa12b38675987e19a241c82cad150a
+size 158897385

Mr.C.B/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "Mr.C.B": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

New/删除多余文件.py

@@ -0,0 +1,25 @@
+import os
+import glob
+import shutil
+
+def remove_files_and_folders(folder_path):
+    for item in os.listdir(folder_path):
+        item_path = os.path.join(folder_path, item)
+
+        if os.path.isfile(item_path) and item not in ["config.json", "G_latest.pth"]:
+            os.remove(item_path)
+            print(f"已删除文件: {item_path}")
+        elif os.path.isdir(item_path):
+            shutil.rmtree(item_path)
+            print(f"已删除文件夹: {item_path}")
+
+# 替换为您的目录路径
+root_directory = os.getcwd()
+
+# 遍历目录下的所有文件夹
+for folder in os.listdir(root_directory):
+    folder_path = os.path.join(root_directory, folder)
+
+    # 确保这是一个文件夹
+    if os.path.isdir(folder_path):
+        remove_files_and_folders(folder_path)

SakuraChiyonoO/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fccb009c7be7c5cf025b5b04b2303c076dbd0e97cd18dbb40c8ae019b8afec7
+size 158897385

SakuraChiyonoO/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "SakuraChiyonoO": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

SuperCreek/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77c21adf0f97ba218aa0a5a7559c8b44e20c27a8956bafd859a0ba7578471ea
+size 158897385

SuperCreek/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "SuperCreek": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

SymboliRudolf/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f77b049123c5d799226b01abe0ca420c5a6b98211f77f0a8f35df79ad27f4bc
+size 158897385

SymboliRudolf/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "SymboliRudolf": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

TamamoCross/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb8c44dadd8f1683e89c98460c8486949f2c3f289279b025bb25c5c7948b465
+size 158897385

TamamoCross/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "TamamoCross": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

TokaiTeio/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51687d169a6697bd0bce491b2bd7140bd5fe0e91ecf3f5c25f3c0907d13ac2f7
+size 158897385

TokaiTeio/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "TokaiTeio": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

WinningTicket/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c593c322712f8bbeef462973f96319fdd1083776596fc71173cb173b599f5e16
+size 158897385

WinningTicket/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "WinningTicket": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

WonderAcute/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223a6fbd7335a686f48e97f0d5d778801dc95f9f175e264dea75d3e0f53fb232
+size 158897385

WonderAcute/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "WonderAcute": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

YamaninZephyr/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df7ce0886e6478e639a33fe946e8736a92cf3ca9c27cc0d3f14c591caad444f
+size 158897385

YamaninZephyr/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "YamaninZephyr": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}

ZennoRobRoy/G_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6720ca4387a6306728219fc3f1d136c8e43ee7bb1caace8cf882b32ed6de41
+size 158897385

ZennoRobRoy/config.json

@@ -0,0 +1,145 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 32,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "final_annotation_train.txt",
+    "validation_files": "final_annotation_val.txt",
+    "text_cleaners": [
+      "zh_ja_mixture_cleaners"
+    ],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true
+  },
+  "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
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": {
+    "ZennoRobRoy": 0
+  },
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "~",
+    "\u2026",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u02a6",
+    "\u026f",
+    "\u0279",
+    "\u0259",
+    "\u0265",
+    "\u207c",
+    "\u02b0",
+    "`",
+    "\u2192",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}