add 20221231-5speaker

.gitignore

@@ -2,5 +2,6 @@
 
 
 */*/good/**
+*/*/base/**
 */*/last/**
 */*/backup/**

vits/20221231-5speaker/best/D_67200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3185311bf69159e30631f50b800794ae74799fa62ddd91cbfea2dd152a0a583
+size 561098185

vits/20221231-5speaker/best/G_67200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4923d2da9e543e995427daad44a9c2a40b9e6c6549d391d0d96395d6f7b5de0
+size 476800561

vits/20221231-5speaker/best/config.json

@@ -0,0 +1,63 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 200,
+    "seed": 1234,
+    "epochs": 800,
+    "learning_rate": 2e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 16,
+    "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":"filelists/train_filelist.txt.cleaned",
+    "validation_files":"filelists/val_filelist.txt.cleaned",
+    "text_cleaners":["japanese_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": 7,
+    "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": 7,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": [
+    "Akaset",
+    "Asuna",
+    "Aurora",
+    "Silenus",
+    "AkasetNS",
+    "\u978d\u99ac\u5c0f\u6625",
+    "\u5728\u539f\u4e03\u6d77"
+  ],
+  "symbols":["_",",",".","!","?","-","A","E","I","N","O","Q","U","a","b","d","e","f","g","h","i","j","k","m","n","o","p","r","s","t","u","v","w","y","z","\u0283","\u02a7","\u2193","\u2191"," "]
+}

vits/20221231-5speaker/config.json

@@ -0,0 +1,63 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 200,
+    "seed": 1234,
+    "epochs": 800,
+    "learning_rate": 2e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 16,
+    "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":"filelists/train_filelist.txt.cleaned",
+    "validation_files":"filelists/val_filelist.txt.cleaned",
+    "text_cleaners":["japanese_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": 7,
+    "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": 7,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "speakers": [
+    "Akaset",
+    "Asuna",
+    "Aurora",
+    "Silenus",
+    "AkasetNS",
+    "\u978d\u99ac\u5c0f\u6625",
+    "\u5728\u539f\u4e03\u6d77"
+  ],
+  "symbols":["_",",",".","!","?","-","A","E","I","N","O","Q","U","a","b","d","e","f","g","h","i","j","k","m","n","o","p","r","s","t","u","v","w","y","z","\u0283","\u02a7","\u2193","\u2191"," "]
+}

vits/20260109-7speaker/config.json

@@ -0,0 +1,98 @@
+{
+  "train": {
+    "log_interval": 800,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 2000,
+    "learning_rate": 2e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 16,
+    "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":"filelists/train_filelist.txt.cleaned",
+    "validation_files":"filelists/val_filelist.txt.cleaned",
+    "text_cleaners":["japanese_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": 7,
+    "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": [
+    "Aoling","Clarice","Cecilia","Aria","Superbia","Louisa","Kokkoro"
+  ],
+  "symbols": [
+    "_",
+    ",",
+    ".",
+    "!",
+    "?",
+    "-",
+    "A",
+    "E",
+    "I",
+    "N",
+    "O",
+    "Q",
+    "U",
+    "a",
+    "b",
+    "d",
+    "e",
+    "f",
+    "g",
+    "h",
+    "i",
+    "j",
+    "k",
+    "m",
+    "n",
+    "o",
+    "p",
+    "r",
+    "s",
+    "t",
+    "u",
+    "v",
+    "w",
+    "y",
+    "z",
+    "\u0283",
+    "\u02a7",
+    "\u2193",
+    "\u2191",
+    " "
+  ]
+}