Upload tokenizer

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86684c9285ff3483ec4dcd52d9a56b1fb5184d9473774d59c305597c98e3b04b
+size 250003

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "do_upper_case": false,
+  "eos_token": "</s>",
+  "lang_codes": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tgt_lang": null,
+  "tokenizer_class": "Speech2TextTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,1002 @@
+{
+  "<s>": 0,
+  "<pad>": 1,
+  "</s>": 2,
+  "<unk>": 3,
+  "<ar>": 4,
+  "<de>": 5,
+  "<el>": 6,
+  "<es>": 7,
+  "<fr>": 8,
+  "<it>": 9,
+  "<pt>": 10,
+  "<ru>": 11,
+  "\u2581": 12,
+  "s": 13,
+  ",": 14,
+  "a": 15,
+  "\u2581a": 16,
+  "\u2581\"": 17,
+  "\u2581de": 18,
+  "r": 19,
+  "i": 20,
+  ".\"": 21,
+  "e": 22,
+  "n": 23,
+  "u": 24,
+  "o": 25,
+  "\u2581que": 26,
+  "re": 27,
+  "'": 28,
+  "m": 29,
+  "c": 30,
+  ".": 31,
+  "l": 32,
+  "t": 33,
+  "ra": 34,
+  "\u2581la": 35,
+  "\u00e9": 36,
+  "p": 37,
+  "te": 38,
+  "to": 39,
+  "ta": 40,
+  "er": 41,
+  "\u2581di": 42,
+  "ca": 43,
+  "f": 44,
+  "\u2581en": 45,
+  "g": 46,
+  "\u2581un": 47,
+  "co": 48,
+  "\u2581se": 49,
+  "\u2581con": 50,
+  "da": 51,
+  "ci": 52,
+  "de": 53,
+  "le": 54,
+  "ti": 55,
+  "ce": 56,
+  "la": 57,
+  "d": 58,
+  "ma": 59,
+  "ro": 60,
+  "\u0435": 61,
+  "is": 62,
+  "li": 63,
+  "do": 64,
+  "en": 65,
+  "\u2581me": 66,
+  "pe": 67,
+  "\u2581e": 68,
+  "no": 69,
+  "es": 70,
+  "ar": 71,
+  "\u0441": 72,
+  "\u2581o": 73,
+  "ve": 74,
+  "\u2581es": 75,
+  "ne": 76,
+  "mo": 77,
+  "z": 78,
+  "va": 79,
+  "na": 80,
+  "di": 81,
+  "\u2581y": 82,
+  "\u2581no": 83,
+  "\u0443": 84,
+  "ri": 85,
+  "in": 86,
+  "lo": 87,
+  "b": 88,
+  "mos": 89,
+  "\u2581le": 90,
+  "vo": 91,
+  "\u2581in": 92,
+  "\u2581po": 93,
+  "me": 94,
+  "\u03bd": 95,
+  "\u2581ma": 96,
+  "\u00ed": 97,
+  "ni": 98,
+  "on": 99,
+  "\u00e1": 100,
+  "\u2581c": 101,
+  "y": 102,
+  "-": 103,
+  "que": 104,
+  "h": 105,
+  "\u03c3": 106,
+  "\u0627": 107,
+  "\u2581fa": 108,
+  "mi": 109,
+  "\u043c": 110,
+  "est": 111,
+  "vi": 112,
+  "se": 113,
+  "\u2581el": 114,
+  "ba": 115,
+  "as": 116,
+  "\u0438": 117,
+  "\u043e": 118,
+  "an": 119,
+  "gu": 120,
+  "ment": 121,
+  "al": 122,
+  "\u03b1": 123,
+  "\u03b9": 124,
+  ":": 125,
+  "\u2581\u00e0": 126,
+  "\u00f3": 127,
+  "\u03b5": 128,
+  "\u03bf": 129,
+  "\u064a": 130,
+  "ur": 131,
+  "v": 132,
+  "\u2581per": 133,
+  "\u044f": 134,
+  "\u2581pro": 135,
+  "\u2581des": 136,
+  "si": 137,
+  "po": 138,
+  "\u2581si": 139,
+  "\u03bb": 140,
+  "\u2581\u00e9": 141,
+  "\u2581che": 142,
+  "\u2581et": 143,
+  "\"\"": 144,
+  "it": 145,
+  "os": 146,
+  "\u2581mi": 147,
+  "\u03c1": 148,
+  "\u03c2": 149,
+  "\u2581d": 150,
+  "\u043d": 151,
+  "\u2581l": 152,
+  "\u2581pas": 153,
+  "\u2581su": 154,
+  "\u0430": 155,
+  "\u2581do": 156,
+  "res": 157,
+  "tro": 158,
+  "go": 159,
+  "\u03ac": 160,
+  "\u2581qui": 161,
+  "\u0644": 162,
+  "\u0645": 163,
+  "so": 164,
+  "nd": 165,
+  "E": 166,
+  "\u0440": 167,
+  "\u2581qu": 168,
+  "ge": 169,
+  "lle": 170,
+  "sta": 171,
+  "\u2581una": 172,
+  "\u0442": 173,
+  "\u044b": 174,
+  "or": 175,
+  "tra": 176,
+  "\u2581par": 177,
+  "ir": 178,
+  "\u2581al": 179,
+  "\u2581les": 180,
+  "\u0437": 181,
+  "\u2581da": 182,
+  "t\u00e9": 183,
+  "A": 184,
+  "mente": 185,
+  "\u0432": 186,
+  "gi": 187,
+  "\u0646": 188,
+  "tu": 189,
+  "\u2581il": 190,
+  "\u2581so": 191,
+  "\u2581ne": 192,
+  "\u0648": 193,
+  "ch": 194,
+  "\u043d\u043e": 195,
+  "\u0442\u043e": 196,
+  "\u2581vi": 197,
+  "\u062a": 198,
+  "ga": 199,
+  "\u2581eu": 200,
+  "fi": 201,
+  "\u2581com": 202,
+  "pa": 203,
+  "\u0434": 204,
+  "\u2581ha": 205,
+  "M": 206,
+  "lu": 207,
+  "\u03c4": 208,
+  "\u0439": 209,
+  "?": 210,
+  "\u043b": 211,
+  "\u2581lo": 212,
+  "\u03bc": 213,
+  "\u2581je": 214,
+  "bi": 215,
+  "\u2581para": 216,
+  "ter": 217,
+  "nt": 218,
+  "\u043f": 219,
+  "\u03ba": 220,
+  "\u03cc": 221,
+  "x": 222,
+  "ai": 223,
+  "\u03ad": 224,
+  "\u2581\u0441": 225,
+  "\u00e3o": 226,
+  "\u0631": 227,
+  "\u2581sa": 228,
+  "ndo": 229,
+  "\u2581por": 230,
+  "\u2581pa": 231,
+  "sso": 232,
+  "ten": 233,
+  "\u043a": 234,
+  "tre": 235,
+  "\u043d\u0438": 236,
+  "\u2581um": 237,
+  "\u0442\u044c": 238,
+  "\u2581los": 239,
+  "\u03af": 240,
+  "\u2581\u0627\u0644": 241,
+  "qui": 242,
+  "?\"": 243,
+  "un": 244,
+  "\u2581est": 245,
+  "\u2581vous": 246,
+  "lla": 247,
+  "\u2581j": 248,
+  "\u2581pour": 249,
+  "\u03b7": 250,
+  "\u0440\u0430": 251,
+  "us": 252,
+  "il": 253,
+  "tion": 254,
+  "\u2581ce": 255,
+  "\u00e8": 256,
+  "\u2581n\u00e3o": 257,
+  "\u2581uma": 258,
+  "du": 259,
+  "\u0445": 260,
+  "\u0639": 261,
+  "\u00eda": 262,
+  "\u043a\u043e": 263,
+  "C": 264,
+  "\u2581\"\"": 265,
+  "che": 266,
+  "\u0628": 267,
+  "\u2581une": 268,
+  "he": 269,
+  ")": 270,
+  "\u2581\u0432": 271,
+  "\u2581C": 272,
+  "O": 273,
+  "Y": 274,
+  "\u2581\u0438": 275,
+  "\u2581esta": 276,
+  "\u2581del": 277,
+  "ux": 278,
+  "ut": 279,
+  "ria": 280,
+  "k": 281,
+  "\u2581pre": 282,
+  "ent": 283,
+  "I": 284,
+  "\u0433": 285,
+  "za": 286,
+  "\u2581E": 287,
+  "\u0647": 288,
+  "\u2581dans": 289,
+  "gra": 290,
+  "ente": 291,
+  "\u2581\u043f\u043e": 292,
+  "\u2581gente": 293,
+  "\u2581pu": 294,
+  "cha": 295,
+  "\u043b\u0438": 296,
+  "\u2581mais": 297,
+  "\u2581na": 298,
+  "\u2581ou": 299,
+  "\u2581nos": 300,
+  "jo": 301,
+  "R": 302,
+  "\u03b3": 303,
+  "\u2581A": 304,
+  "\u03c9": 305,
+  "\u2581va": 306,
+  "\u2581como": 307,
+  "1": 308,
+  "\u0643": 309,
+  "\u03b4": 310,
+  "\u0441\u0442": 311,
+  "D": 312,
+  "pi": 313,
+  "\u2581comp": 314,
+  "\u2581em": 315,
+  "ble": 316,
+  "\u0433\u043e": 317,
+  "P": 318,
+  "\u2581pr": 319,
+  "\u2581mon": 320,
+  "\u2581tem": 321,
+  "\u062f": 322,
+  "\u2581du": 323,
+  "\u03c0": 324,
+  "\u0431": 325,
+  "\u2581\u043d\u0430": 326,
+  "\u2581pra": 327,
+  "\u03c7": 328,
+  "\u2581\u00e8": 329,
+  "\u0432\u043e": 330,
+  "ces": 331,
+  "\u0436": 332,
+  "\u0448": 333,
+  "\u2581au": 334,
+  "ci\u00f3n": 335,
+  "\u2581on": 336,
+  "ha": 337,
+  "\u2581d\u00e9": 338,
+  "sse": 339,
+  "0": 340,
+  "ste": 341,
+  "nos": 342,
+  "\u0623": 343,
+  "\u2581cu": 344,
+  "\u2581mu": 345,
+  "\u044e": 346,
+  "ver": 347,
+  "les": 348,
+  "\u00ea": 349,
+  "je": 350,
+  "N": 351,
+  "ando": 352,
+  "\u0432\u0430": 353,
+  "\u00fa": 354,
+  "\u03bf\u03c5": 355,
+  "\u2581ho": 356,
+  "mp": 357,
+  "pre": 358,
+  "w": 359,
+  "ho": 360,
+  "\u0442\u0435": 361,
+  "\u03c4\u03b1": 362,
+  "cia": 363,
+  "\u03ae": 364,
+  "sti": 365,
+  "\u03b5\u03b9": 366,
+  "\u2581\u00ab": 367,
+  "\u0629": 368,
+  "\u2581P": 369,
+  "nta": 370,
+  "\u2019": 371,
+  "cer": 372,
+  "F": 373,
+  "\u0434\u0435": 374,
+  "\u2581ser": 375,
+  "\u2581todo": 376,
+  "ja": 377,
+  "L": 378,
+  "zi": 379,
+  "\u2581tra": 380,
+  "\u2581S": 381,
+  "qu": 382,
+  "ado": 383,
+  "chi": 384,
+  "nde": 385,
+  "be": 386,
+  "\u00e7a": 387,
+  "\u03c5": 388,
+  "nu": 389,
+  "ue": 390,
+  "\u2581est\u00e1": 391,
+  "\u2581(": 392,
+  "\u03c4\u03b7": 393,
+  "dos": 394,
+  "\u043b\u044c": 395,
+  "rio": 396,
+  "\u2581non": 397,
+  "\u0633": 398,
+  "Et": 399,
+  "\u03bc\u03b5": 400,
+  "\u0440\u043e": 401,
+  "\u044c": 402,
+  "\u043d\u0430": 403,
+  "\u2581plus": 404,
+  "ssa": 405,
+  "forma": 406,
+  "bo": 407,
+  "\u2581tu": 408,
+  "ssi": 409,
+  "tar": 410,
+  "\u03b8": 411,
+  "ante": 412,
+  "nto": 413,
+  "\u2581las": 414,
+  "\u2581T": 415,
+  "\u2581sur": 416,
+  "gen": 417,
+  "nti": 418,
+  "gar": 419,
+  "ant": 420,
+  "\u043b\u0430": 421,
+  "V": 422,
+  "io": 423,
+  "No": 424,
+  "\u2581nous": 425,
+  "\u2581fo": 426,
+  "ven": 427,
+  "\u0434\u0430": 428,
+  "\u2581era": 429,
+  "cul": 430,
+  "ez": 431,
+  "\u2581\u043d\u0435": 432,
+  "\u2581\u03c0": 433,
+  "llo": 434,
+  "ul": 435,
+  "bu": 436,
+  "tto": 437,
+  "r\u00e9": 438,
+  "\u043a\u0430": 439,
+  "\u0435\u043d": 440,
+  "gli": 441,
+  "\u2581m\u00e1s": 442,
+  "\u2581ver": 443,
+  "ie": 444,
+  "idade": 445,
+  "\u2581porque": 446,
+  "\u2581\u00e7a": 447,
+  "La": 448,
+  "...": 449,
+  "\u2581\u0447\u0442\u043e": 450,
+  "\u03c0\u03bf": 451,
+  "tri": 452,
+  "iamo": 453,
+  "elle": 454,
+  "n\u00e9": 455,
+  "\u0642": 456,
+  "\u03bc\u03b1": 457,
+  "\u2581\u00bf": 458,
+  "G": 459,
+  "\u0641": 460,
+  "\u062d": 461,
+  "\u2581tout": 462,
+  "H": 463,
+  "idad": 464,
+  "\u043b\u043e": 465,
+  "\u2581voc\u00ea": 466,
+  "\u2581ex": 467,
+  "sion": 468,
+  "mento": 469,
+  "au": 470,
+  "\u2581r\u00e9": 471,
+  "\u2581pl": 472,
+  "J": 473,
+  "\u2581come": 474,
+  "\u043b\u0435": 475,
+  "ide": 476,
+  "ff": 477,
+  "\u0435\u0440": 478,
+  "\u00e8re": 479,
+  "T": 480,
+  "\u0435\u0442": 481,
+  "\u0451": 482,
+  "Je": 483,
+  "cio": 484,
+  "tte": 485,
+  "S": 486,
+  "cos": 487,
+  "\u2581bo": 488,
+  "5": 489,
+  "\u2581ve": 490,
+  "cre": 491,
+  "\u0441\u044f": 492,
+  "\u0442\u0438": 493,
+  "tant": 494,
+  "\u2581\u03bd\u03b1": 495,
+  "ol": 496,
+  "\u2581\u044d\u0442\u043e": 497,
+  "cri": 498,
+  "\u2581imp": 499,
+  "m\u00e9": 500,
+  "\u2581B": 501,
+  ";": 502,
+  "\u2581bien": 503,
+  "Es": 504,
+  "\u2581fait": 505,
+  "\u2581son": 506,
+  "\u03c4\u03b9": 507,
+  "ju": 508,
+  "\u03c6": 509,
+  "\u2581\u00bb": 510,
+  "\u2581car": 511,
+  "\u2581be": 512,
+  "Il": 513,
+  "\u2581avec": 514,
+  "\u0447": 515,
+  "ine": 516,
+  "\u03ce": 517,
+  "dia": 518,
+  "tura": 519,
+  "Eu": 520,
+  "ali": 521,
+  "\u2581comme": 522,
+  "2": 523,
+  "\u043e\u0442": 524,
+  "!": 525,
+  "\u00e7\u00e3o": 526,
+  "\u00e0": 527,
+  "Por": 528,
+  "\u0436\u0435": 529,
+  "\u2581muito": 530,
+  "ser": 531,
+  "t\u00e0": 532,
+  "\u2581for": 533,
+  "sent": 534,
+  "\u2581\u03c4\u03bf": 535,
+  "\u2581:": 536,
+  "cho": 537,
+  "\u03c4\u03b5": 538,
+  "Le": 539,
+  "\u2581\u043e": 540,
+  "\u2581pi": 541,
+  "\u2581inter": 542,
+  "tru": 543,
+  "\u2581ele": 544,
+  "\u062c": 545,
+  "\u2581\u03ba\u03b1\u03b9": 546,
+  "tti": 547,
+  "bra": 548,
+  "zione": 549,
+  "3": 550,
+  "Un": 551,
+  "l\u00e0": 552,
+  "\u00eatre": 553,
+  "\u2581esto": 554,
+  "\u0434\u043e": 555,
+  "En": 556,
+  "\u2581vida": 557,
+  "\u2581esse": 558,
+  "\u2581Ma": 559,
+  "\u043c\u0438": 560,
+  "ons": 561,
+  "\u03b1\u03bd": 562,
+  "\u0442\u0430": 563,
+  "\u2581emp": 564,
+  "\u2581parti": 565,
+  "ance": 566,
+  "tica": 567,
+  "\u2581ri": 568,
+  "\u03b5\u03af": 569,
+  "\u2581sono": 570,
+  "\u043c\u0430": 571,
+  "\u0440\u0438": 572,
+  "\u03b9\u03b1": 573,
+  "\u03cd": 574,
+  "\u2581faire": 575,
+  "\u2581fin": 576,
+  "\u043e\u0431": 577,
+  "\u2581mundo": 578,
+  "\u0434\u0438": 579,
+  "\u2581vie": 580,
+  "Q": 581,
+  "ation": 582,
+  "De": 583,
+  "\u2581cosa": 584,
+  "ient": 585,
+  "\u258120": 586,
+  "\u03b2": 587,
+  "\u043d\u0435": 588,
+  "\u2581li": 589,
+  "ber": 590,
+  "\u2581isso": 591,
+  "vers": 592,
+  "\u0435\u043c": 593,
+  "\u2581cor": 594,
+  "\u2581persona": 595,
+  "\u2581foi": 596,
+  "bre": 597,
+  "\u03c1\u03b1": 598,
+  "port": 599,
+  "\u2581entre": 600,
+  "\u0447\u0435": 601,
+  "\u2581moi": 602,
+  "\u2581\u043f\u0440\u043e": 603,
+  "\u2581essa": 604,
+  "bri": 605,
+  "l\u00e9": 606,
+  "nder": 607,
+  "\u2581sont": 608,
+  "cette": 609,
+  "a\u00e7\u00e3o": 610,
+  "\u0432\u0438": 611,
+  "U": 612,
+  "\u0627\u0644": 613,
+  "\u043a\u0438": 614,
+  "inte": 615,
+  "\u2581real": 616,
+  "\u060c": 617,
+  "\u2581exp": 618,
+  "\u0431\u043e": 619,
+  "\u2581sol": 620,
+  "\u2581col": 621,
+  "Que": 622,
+  "\u2581tiene": 623,
+  "encia": 624,
+  "\u2581voi": 625,
+  "\u2581pensa": 626,
+  "!\"": 627,
+  "\u2581\u043c\u043e": 628,
+  "r\u00eda": 629,
+  "\u00f1o": 630,
+  "tiva": 631,
+  "\u2581vol": 632,
+  "\u2581cap": 633,
+  "fica": 634,
+  "\u2581all": 635,
+  "\u2581peu": 636,
+  "\u00f1": 637,
+  "rie": 638,
+  "\u0635": 639,
+  "\u00f4": 640,
+  "B": 641,
+  "contr": 642,
+  "4": 643,
+  "\u2581qual": 644,
+  "\u2581\u0437\u0430": 645,
+  "\u2581vai": 646,
+  "\u2581questo": 647,
+  "\u0630": 648,
+  "mbi": 649,
+  "\u0634": 650,
+  "\u2581suis": 651,
+  "gio": 652,
+  "Si": 653,
+  "\u2581quando": 654,
+  "Se": 655,
+  "vent": 656,
+  "nza": 657,
+  "\u00e7o": 658,
+  "\u0447\u0430": 659,
+  "\u043c\u0443": 660,
+  "\"": 661,
+  "\u2581vez": 662,
+  "\u00bb": 663,
+  "v\u00e9": 664,
+  "\u0444": 665,
+  "nho": 666,
+  "\u2581pi\u00f9": 667,
+  "\u2014": 668,
+  "\u2581\"(": 669,
+  "prime": 670,
+  "\u2581minha": 671,
+  "\u2581peut": 672,
+  "\u2581\u0431\u044b": 673,
+  "\u2581hacer": 674,
+  "On": 675,
+  "\u03c1\u03bf": 676,
+  "\u03ba\u03b1": 677,
+  "Par": 678,
+  "00": 679,
+  "ntes": 680,
+  "cur": 681,
+  "9": 682,
+  "\u2581muy": 683,
+  "\u00e9tait": 684,
+  "\u2581grande": 685,
+  "\u00e2": 686,
+  "\u2581trans": 687,
+  "Com": 688,
+  "\u2581m\u00eame": 689,
+  "act": 690,
+  "\u2581fazer": 691,
+  "\u0418": 692,
+  "\u062e": 693,
+  "\u2581toda": 694,
+  "\u2581\u043a\u0430\u043a": 695,
+  "\u2581momento": 696,
+  "\u2581sobre": 697,
+  "\u2581n\u00f3s": 698,
+  "\u2581coisa": 699,
+  "\u03be": 700,
+  "\u0441\u0442\u0430": 701,
+  "8": 702,
+  "\u0637": 703,
+  "\u044d": 704,
+  "6": 705,
+  "\u03b6": 706,
+  "j": 707,
+  "\u00c9": 708,
+  "\u0446": 709,
+  "\u00f2": 710,
+  "W": 711,
+  "7": 712,
+  "\u041d": 713,
+  "\u0649": 714,
+  "%": 715,
+  "\u0412": 716,
+  "\u00f9": 717,
+  "\u062b": 718,
+  "\u00ec": 719,
+  "\u064b": 720,
+  "K": 721,
+  "\u0625": 722,
+  "\u00fc": 723,
+  "\u041f": 724,
+  "\u00ee": 725,
+  "\u0636": 726,
+  "[": 727,
+  "\u0421": 728,
+  "]": 729,
+  "\u041c": 730,
+  "\u039a": 731,
+  "\u00e4": 732,
+  "\u00a1": 733,
+  "\u0632": 734,
+  "\u266a": 735,
+  "\u00fb": 736,
+  "\u041a": 737,
+  "\u0391": 738,
+  "\u00e3": 739,
+  "\u0621": 740,
+  "\u0395": 741,
+  "\u00f5": 742,
+  "\u041e": 743,
+  "\u0422": 744,
+  "\u00bf": 745,
+  "\u063a": 746,
+  "\u042f": 747,
+  "\u03a4": 748,
+  "\u0410": 749,
+  "\u042d": 750,
+  "\u0414": 751,
+  "\u00f6": 752,
+  "\u0626": 753,
+  "\u00c8": 754,
+  "\u03a0": 755,
+  "\u0153": 756,
+  "X": 757,
+  "Z": 758,
+  "\u03c8": 759,
+  "\u039c": 760,
+  "\u03a3": 761,
+  "\u061f": 762,
+  "\u0651": 763,
+  "\u00c3": 764,
+  "\u0393": 765,
+  "\u0638": 766,
+  "\u201c": 767,
+  "\u201d": 768,
+  "\u0415": 769,
+  ">": 770,
+  "<": 771,
+  "/": 772,
+  "\u0394": 773,
+  "\u039f": 774,
+  "\u0388": 775,
+  "\u00ab": 776,
+  "\u00c0": 777,
+  "\u0427": 778,
+  "\u064f": 779,
+  "\u0411": 780,
+  "\u0423": 781,
+  "\u0417": 782,
+  "\u00df": 783,
+  "\u00e7": 784,
+  "\u0420": 785,
+  "\u0622": 786,
+  "\u00a9": 787,
+  "\u266b": 788,
+  "\u038c": 789,
+  "\u00ef": 790,
+  "q": 791,
+  "\u0397": 792,
+  "\u20ac": 793,
+  "\u039d": 794,
+  "\u0624": 795,
+  "\u0398": 796,
+  "\u2013": 797,
+  "\u041b": 798,
+  "\u03a7": 799,
+  "\u00c1": 800,
+  "\u0413": 801,
+  "\u0392": 802,
+  "\u039b": 803,
+  "\u064e": 804,
+  "\u0425": 805,
+  "\u0389": 806,
+  "\u03a6": 807,
+  "\u064d": 808,
+  "$": 809,
+  "\u03ca": 810,
+  "\u0399": 811,
+  "\u0386": 812,
+  "\u0424": 813,
+  "\u0301": 814,
+  "\u017d": 815,
+  "\u0650": 816,
+  "&": 817,
+  "\u0652": 818,
+  "\u03a5": 819,
+  "+": 820,
+  "\u00b0": 821,
+  "\u0428": 822,
+  "\u039e": 823,
+  "\u00eb": 824,
+  "\u0416": 825,
+  "\u064c": 826,
+  "\u03a1": 827,
+  "\u00ca": 828,
+  "\u0640": 829,
+  "\u2018": 830,
+  "\u00cd": 831,
+  "\u00d3": 832,
+  "\u2021": 833,
+  "\u0426": 834,
+  "\u061b": 835,
+  "\u03a9": 836,
+  "#": 837,
+  "(": 838,
+  "\u02c6": 839,
+  "\u00c2": 840,
+  "\u2039": 841,
+  "=": 842,
+  "\u042e": 843,
+  "\u00dc": 844,
+  "\u00d6": 845,
+  "\u00a7": 846,
+  "\u00d4": 847,
+  "\u06a8": 848,
+  "\u2015": 849,
+  "\u00da": 850,
+  "\u017c": 851,
+  "\u00e6": 852,
+  "*": 853,
+  "@": 854,
+  "\u04a3": 855,
+  "\u203a": 856,
+  "\u0303": 857,
+  "\u0456": 858,
+  "\u038f": 859,
+  "\u00a2": 860,
+  "\u2212": 861,
+  "\u04e9": 862,
+  "_": 863,
+  "\u00b7": 864,
+  "\u00fd": 865,
+  "\u00e5": 866,
+  "\u5bb6": 867,
+  "\u017e": 868,
+  "`": 869,
+  "\u025b": 870,
+  "\u0107": 871,
+  "\u0113": 872,
+  "\u0254": 873,
+  "\u201e": 874,
+  "\u00f8": 875,
+  "\u660e": 876,
+  "\u00ae": 877,
+  "\u00d1": 878,
+  "\u2030": 879,
+  "|": 880,
+  "\u014d": 881,
+  "\u01ce": 882,
+  "\u0400": 883,
+  "\u066a": 884,
+  "\u0219": 885,
+  "\u04b1": 886,
+  "\u049b": 887,
+  "\u529b": 888,
+  "\u0101": 889,
+  "}": 890,
+  "\u0115": 891,
+  "\u012b": 892,
+  "\u0142": 893,
+  "\u038e": 894,
+  "\u0662": 895,
+  "\u06f0": 896,
+  "\u010d": 897,
+  "\u0119": 898,
+  "\u00d7": 899,
+  "\u8c22": 900,
+  "\u52aa": 901,
+  "\u597d": 902,
+  "\u5929": 903,
+  "\u00a6": 904,
+  "\u011b": 905,
+  "\u0127": 906,
+  "\u016b": 907,
+  "\u03b0": 908,
+  "\u0429": 909,
+  "\u042b": 910,
+  "\u04af": 911,
+  "\u0663": 912,
+  "\u1eba": 913,
+  "\u4e50": 914,
+  "\u798f": 915,
+  "\u5927": 916,
+  "\u04bb": 917,
+  "\u00a3": 918,
+  "\u0493": 919,
+  "^": 920,
+  "\u1ebd": 921,
+  "\u2044": 922,
+  "\u014c": 923,
+  "\u00ce": 924,
+  "\u0419": 925,
+  "\u03a8": 926,
+  "\u03cb": 927,
+  "\u0390": 928,
+  "\u00c4": 929,
+  "\u0144": 930,
+  "\u0396": 931,
+  "\u038a": 932,
+  "\u0308": 933,
+  "\u044a": 934,
+  "\u00c7": 935,
+  "\u662f": 936,
+  "\u00c5": 937,
+  "\u1ff6": 938,
+  "\u221a": 939,
+  "\u6562": 940,
+  "\u1f14": 941,
+  "{": 942,
+  "~": 943,
+  "\u00d2": 944,
+  "\u0102": 945,
+  "\u0103": 946,
+  "\u010c": 947,
+  "\u0131": 948,
+  "\u0152": 949,
+  "\u015f": 950,
+  "\u0161": 951,
+  "\u016f": 952,
+  "\u0171": 953,
+  "\u0401": 954,
+  "\u049a": 955,
+  "\u04d9": 956,
+  "\u0661": 957,
+  "\u0666": 958,
+  "\u0671": 959,
+  "\u06f7": 960,
+  "\u1e47": 961,
+  "\u1f04": 962,
+  "\u1f50": 963,
+  "\u1f76": 964,
+  "\u1fc6": 965,
+  "\u2260": 966,
+  "\u2265": 967,
+  "\u4e22": 968,
+  "\u4e86": 969,
+  "\u4eca": 970,
+  "\u4eec": 971,
+  "\u4f60": 972,
+  "\u52c7": 973,
+  "\u5341": 974,
+  "\u5973": 975,
+  "\u5974": 976,
+  "\u5992": 977,
+  "\u5b50": 978,
+  "\u5b80": 979,
+  "\u5b89": 980,
+  "\u5b9e": 981,
+  "\u5c14": 982,
+  "\u5c81": 983,
+  "\u5e74": 984,
+  "\u5f97": 985,
+  "\u6211": 986,
+  "\u65e5": 987,
+  "\u6708": 988,
+  "\u732b": 989,
+  "\u7530": 990,
+  "\u7537": 991,
+  "\u7f8e": 992,
+  "\u8d1d": 993,
+  "\u8d23": 994,
+  "\u8d5b": 995,
+  "\u015b": 996,
+  "\u0178": 997,
+  "\u0449": 998,
+  "\u4e03": 999
+}