Upload 7 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 177
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "kakao-enterprise/vits-vctk",
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModel"
+  ],
+  "attention_dropout": 0.1,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 3,
+  "duration_predictor_dropout": 0.5,
+  "duration_predictor_filter_channels": 256,
+  "duration_predictor_flow_bins": 10,
+  "duration_predictor_kernel_size": 3,
+  "duration_predictor_num_flows": 4,
+  "duration_predictor_tail_bound": 5.0,
+  "ffn_dim": 768,
+  "ffn_kernel_size": 3,
+  "flow_size": 192,
+  "hidden_act": "relu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 192,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "leaky_relu_slope": 0.1,
+  "model_type": "vits",
+  "noise_scale": 0.667,
+  "noise_scale_duration": 0.8,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 6,
+  "num_speakers": 109,
+  "posterior_encoder_num_wavenet_layers": 16,
+  "prior_encoder_num_flows": 4,
+  "prior_encoder_num_wavenet_layers": 4,
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "sampling_rate": 22050,
+  "speaker_embedding_size": 256,
+  "speaking_rate": 1.0,
+  "spectrogram_bins": 513,
+  "transformers_version": "4.38.2",
+  "upsample_initial_channel": 512,
+  "upsample_kernel_sizes": [
+    16,
+    16,
+    4,
+    4
+  ],
+  "upsample_rates": [
+    8,
+    8,
+    2,
+    2
+  ],
+  "use_bias": true,
+  "use_stochastic_duration_prediction": true,
+  "vocab_size": 178,
+  "wavenet_dilation_rate": 1,
+  "wavenet_dropout": 0.0,
+  "wavenet_kernel_size": 5,
+  "window_size": 4
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a229ee3e8b5d6c43c192ff967d4b433c221af95c85642cd45d7be599e434cb
+size 114365937

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "_",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,223 @@
+{
+    "version": "1.0",
+    "truncation": null,
+    "padding": null,
+    "added_tokens": [
+        {
+            "id": 177,
+            "content": "<unk>",
+            "single_word": false,
+            "lstrip": false,
+            "rstrip": false,
+            "normalized": false,
+            "special": true
+        }
+    ],
+    "normalizer": {
+        "type": "Sequence",
+        "normalizers": [
+            {
+                "type": "Lowercase"
+            },
+            {
+                "type": "Replace",
+                "pattern": {
+                    "Regex": "(?=.)|(?<!^)$"
+                },
+                "content": "_"
+            }
+        ]
+    },
+    "pre_tokenizer": {
+        "type": "Split",
+        "pattern": {
+            "Regex": ""
+        },
+        "behavior": "Isolated",
+        "invert": false
+    },
+    "post_processor": null,
+    "decoder": null,
+    "model": {
+        "vocab": {
+            "_": 0,
+            ";": 1,
+            ":": 2,
+            ",": 3,
+            ".": 4,
+            "!": 5,
+            "?": 6,
+            "\u00a1": 7,
+            "\u00bf": 8,
+            "\u2014": 9,
+            "\u2026": 10,
+            "\"": 11,
+            "\u00ab": 12,
+            "\u00bb": 13,
+            "\u201c": 14,
+            "\u201d": 15,
+            " ": 16,
+            "A": 17,
+            "B": 18,
+            "C": 19,
+            "D": 20,
+            "E": 21,
+            "F": 22,
+            "G": 23,
+            "H": 24,
+            "I": 25,
+            "J": 26,
+            "K": 27,
+            "L": 28,
+            "M": 29,
+            "N": 30,
+            "O": 31,
+            "P": 32,
+            "Q": 33,
+            "R": 34,
+            "S": 35,
+            "T": 36,
+            "U": 37,
+            "V": 38,
+            "W": 39,
+            "X": 40,
+            "Y": 41,
+            "Z": 42,
+            "a": 43,
+            "b": 44,
+            "c": 45,
+            "d": 46,
+            "e": 47,
+            "f": 48,
+            "g": 49,
+            "h": 50,
+            "i": 51,
+            "j": 52,
+            "k": 53,
+            "l": 54,
+            "m": 55,
+            "n": 56,
+            "o": 57,
+            "p": 58,
+            "q": 59,
+            "r": 60,
+            "s": 61,
+            "t": 62,
+            "u": 63,
+            "v": 64,
+            "w": 65,
+            "x": 66,
+            "y": 67,
+            "z": 68,
+            "\u0251": 69,
+            "\u0250": 70,
+            "\u0252": 71,
+            "\u00e6": 72,
+            "\u0253": 73,
+            "\u0299": 74,
+            "\u03b2": 75,
+            "\u0254": 76,
+            "\u0255": 77,
+            "\u00e7": 78,
+            "\u0257": 79,
+            "\u0256": 80,
+            "\u00f0": 81,
+            "\u02a4": 82,
+            "\u0259": 83,
+            "\u0258": 84,
+            "\u025a": 85,
+            "\u025b": 86,
+            "\u025c": 87,
+            "\u025d": 88,
+            "\u025e": 89,
+            "\u025f": 90,
+            "\u0284": 91,
+            "\u0261": 92,
+            "\u0260": 93,
+            "\u0262": 94,
+            "\u029b": 95,
+            "\u0266": 96,
+            "\u0267": 97,
+            "\u0127": 98,
+            "\u0265": 99,
+            "\u029c": 100,
+            "\u0268": 101,
+            "\u026a": 102,
+            "\u029d": 103,
+            "\u026d": 104,
+            "\u026c": 105,
+            "\u026b": 106,
+            "\u026e": 107,
+            "\u029f": 108,
+            "\u0271": 109,
+            "\u026f": 110,
+            "\u0270": 111,
+            "\u014b": 112,
+            "\u0273": 113,
+            "\u0272": 114,
+            "\u0274": 115,
+            "\u00f8": 116,
+            "\u0275": 117,
+            "\u0278": 118,
+            "\u03b8": 119,
+            "\u0153": 120,
+            "\u0276": 121,
+            "\u0298": 122,
+            "\u0279": 123,
+            "\u027a": 124,
+            "\u027e": 125,
+            "\u027b": 126,
+            "\u0280": 127,
+            "\u0281": 128,
+            "\u027d": 129,
+            "\u0282": 130,
+            "\u0283": 131,
+            "\u0288": 132,
+            "\u02a7": 133,
+            "\u0289": 134,
+            "\u028a": 135,
+            "\u028b": 136,
+            "\u2c71": 137,
+            "\u028c": 138,
+            "\u0263": 139,
+            "\u0264": 140,
+            "\u028d": 141,
+            "\u03c7": 142,
+            "\u028e": 143,
+            "\u028f": 144,
+            "\u0291": 145,
+            "\u0290": 146,
+            "\u0292": 147,
+            "\u0294": 148,
+            "\u02a1": 149,
+            "\u0295": 150,
+            "\u02a2": 151,
+            "\u01c0": 152,
+            "\u01c1": 153,
+            "\u01c2": 154,
+            "\u01c3": 155,
+            "\u02c8": 156,
+            "\u02cc": 157,
+            "\u02d0": 158,
+            "\u02d1": 159,
+            "\u02bc": 160,
+            "\u02b4": 161,
+            "\u02b0": 162,
+            "\u02b1": 163,
+            "\u02b2": 164,
+            "\u02b7": 165,
+            "\u02e0": 166,
+            "\u02e4": 167,
+            "\u02de": 168,
+            "\u2193": 169,
+            "\u2191": 170,
+            "\u2192": 171,
+            "\u2197": 172,
+            "\u2198": 173,
+            "null": 174,
+            "\u0329": 175,
+            "'": 176,
+            "<unk>": 177
+        }
+    }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "177": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "_",
+  "phonemize": true,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,179 @@
+{
+  " ": 16,
+  "!": 5,
+  "\"": 11,
+  "'": 176,
+  ",": 3,
+  ".": 4,
+  ":": 2,
+  ";": 1,
+  "?": 6,
+  "A": 17,
+  "B": 18,
+  "C": 19,
+  "D": 20,
+  "E": 21,
+  "F": 22,
+  "G": 23,
+  "H": 24,
+  "I": 25,
+  "J": 26,
+  "K": 27,
+  "L": 28,
+  "M": 29,
+  "N": 30,
+  "O": 31,
+  "P": 32,
+  "Q": 33,
+  "R": 34,
+  "S": 35,
+  "T": 36,
+  "U": 37,
+  "V": 38,
+  "W": 39,
+  "X": 40,
+  "Y": 41,
+  "Z": 42,
+  "_": 0,
+  "a": 43,
+  "b": 44,
+  "c": 45,
+  "d": 46,
+  "e": 47,
+  "f": 48,
+  "g": 49,
+  "h": 50,
+  "i": 51,
+  "j": 52,
+  "k": 53,
+  "l": 54,
+  "m": 55,
+  "n": 56,
+  "o": 57,
+  "p": 58,
+  "q": 59,
+  "r": 60,
+  "s": 61,
+  "t": 62,
+  "u": 63,
+  "v": 64,
+  "w": 65,
+  "x": 66,
+  "y": 67,
+  "z": 68,
+  "¡": 7,
+  "«": 12,
+  "»": 13,
+  "¿": 8,
+  "æ": 72,
+  "ç": 78,
+  "ð": 81,
+  "ø": 116,
+  "ħ": 98,
+  "ŋ": 112,
+  "œ": 120,
+  "ǀ": 152,
+  "ǁ": 153,
+  "ǂ": 154,
+  "ǃ": 155,
+  "ɐ": 70,
+  "ɑ": 69,
+  "ɒ": 71,
+  "ɓ": 73,
+  "ɔ": 76,
+  "ɕ": 77,
+  "ɖ": 80,
+  "ɗ": 79,
+  "ɘ": 84,
+  "ə": 83,
+  "ɚ": 85,
+  "ɛ": 86,
+  "ɜ": 87,
+  "ɝ": 88,
+  "ɞ": 89,
+  "ɟ": 90,
+  "ɠ": 93,
+  "ɡ": 92,
+  "ɢ": 94,
+  "ɣ": 139,
+  "ɤ": 140,
+  "ɥ": 99,
+  "ɦ": 96,
+  "ɧ": 97,
+  "ɨ": 101,
+  "ɪ": 102,
+  "ɫ": 106,
+  "ɬ": 105,
+  "ɭ": 104,
+  "ɮ": 107,
+  "ɯ": 110,
+  "ɰ": 111,
+  "ɱ": 109,
+  "ɲ": 114,
+  "ɳ": 113,
+  "ɴ": 115,
+  "ɵ": 117,
+  "ɶ": 121,
+  "ɸ": 118,
+  "ɹ": 123,
+  "ɺ": 124,
+  "ɻ": 126,
+  "ɽ": 129,
+  "ɾ": 125,
+  "ʀ": 127,
+  "ʁ": 128,
+  "ʂ": 130,
+  "ʃ": 131,
+  "ʄ": 91,
+  "ʈ": 132,
+  "ʉ": 134,
+  "ʊ": 135,
+  "ʋ": 136,
+  "ʌ": 138,
+  "ʍ": 141,
+  "ʎ": 143,
+  "ʏ": 144,
+  "ʐ": 146,
+  "ʑ": 145,
+  "ʒ": 147,
+  "ʔ": 148,
+  "ʕ": 150,
+  "ʘ": 122,
+  "ʙ": 74,
+  "ʛ": 95,
+  "ʜ": 100,
+  "ʝ": 103,
+  "ʟ": 108,
+  "ʡ": 149,
+  "ʢ": 151,
+  "ʤ": 82,
+  "ʧ": 133,
+  "ʰ": 162,
+  "ʱ": 163,
+  "ʲ": 164,
+  "ʴ": 161,
+  "ʷ": 165,
+  "ʼ": 160,
+  "ˈ": 156,
+  "ˌ": 157,
+  "ː": 158,
+  "ˑ": 159,
+  "˞": 168,
+  "ˠ": 166,
+  "ˤ": 167,
+  "̩": 175,
+  "β": 75,
+  "θ": 119,
+  "χ": 142,
+  "ᵻ": 177,
+  "—": 9,
+  "“": 14,
+  "”": 15,
+  "…": 10,
+  "↑": 170,
+  "→": 171,
+  "↓": 169,
+  "↗": 172,
+  "↘": 173,
+  "ⱱ": 137
+}