Upload tokenizer

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "<unk>": 177
+  "<unk>": 38
 }

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "pad_token": {
-    "content": "_",
+    "content": "k",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2,14 +2,14 @@
   "add_blank": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "_",
+      "content": "k",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "177": {
+    "38": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -20,11 +20,11 @@
   },
   "clean_up_tokenization_spaces": true,
   "is_uroman": false,
-  "language": null,
-  "model_max_length": 1000000000000000019884624838656,
+  "language": "eng",
+  "model_max_length": 4096,
   "normalize": true,
-  "pad_token": "_",
-  "phonemize": true,
+  "pad_token": "k",
+  "phonemize": false,
   "tokenizer_class": "VitsTokenizer",
   "unk_token": "<unk>",
   "verbose": false

vocab.json

@@ -1,179 +1,40 @@
 {
-  " ": 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
+  " ": 19,
+  "'": 1,
+  "-": 14,
+  "0": 23,
+  "1": 15,
+  "2": 28,
+  "3": 11,
+  "4": 27,
+  "5": 35,
+  "6": 36,
+  "_": 30,
+  "a": 26,
+  "b": 24,
+  "c": 12,
+  "d": 5,
+  "e": 7,
+  "f": 20,
+  "g": 37,
+  "h": 6,
+  "i": 18,
+  "j": 16,
+  "k": 0,
+  "l": 21,
+  "m": 17,
+  "n": 29,
+  "o": 22,
+  "p": 13,
+  "q": 34,
+  "r": 25,
+  "s": 8,
+  "t": 33,
+  "u": 4,
+  "v": 32,
+  "w": 9,
+  "x": 31,
+  "y": 3,
+  "z": 2,
+  "–": 10
 }