SubSegGPT-strict / vocab.json
francois-meyer's picture
Upload main checkpoint (epoch_1B)
bfe13ba verified
Raw
History Blame Contribute Delete
9.77 kB
{
"<pad>": 0,
"<bos>": 1,
"<eos>": 2,
"<seg>": 3,
"<unk>": 4,
"A": 5,
"B": 6,
"C": 7,
"D": 8,
"E": 9,
"F": 10,
"G": 11,
"H": 12,
"I": 13,
"J": 14,
"K": 15,
"L": 16,
"M": 17,
"N": 18,
"O": 19,
"P": 20,
"Q": 21,
"R": 22,
"S": 23,
"T": 24,
"U": 25,
"V": 26,
"W": 27,
"X": 28,
"Y": 29,
"Z": 30,
"a": 31,
"b": 32,
"c": 33,
"d": 34,
"e": 35,
"f": 36,
"g": 37,
"h": 38,
"i": 39,
"j": 40,
"k": 41,
"l": 42,
"m": 43,
"n": 44,
"o": 45,
"p": 46,
"q": 47,
"r": 48,
"s": 49,
"t": 50,
"u": 51,
"v": 52,
"w": 53,
"x": 54,
"y": 55,
"z": 56,
"º": 57,
"À": 58,
"Á": 59,
"Â": 60,
"Ã": 61,
"Ä": 62,
"Å": 63,
"Æ": 64,
"Ç": 65,
"È": 66,
"É": 67,
"Ê": 68,
"Ë": 69,
"Ì": 70,
"Í": 71,
"Î": 72,
"Ï": 73,
"Ð": 74,
"Ñ": 75,
"Ò": 76,
"Ó": 77,
"Ô": 78,
"Õ": 79,
"Ö": 80,
"Ø": 81,
"Ù": 82,
"Ú": 83,
"Û": 84,
"Ü": 85,
"Ý": 86,
"Þ": 87,
"ß": 88,
"à": 89,
"á": 90,
"â": 91,
"ã": 92,
"ä": 93,
"å": 94,
"æ": 95,
"ç": 96,
"è": 97,
"é": 98,
"ê": 99,
"ë": 100,
"ì": 101,
"í": 102,
"î": 103,
"ï": 104,
"ð": 105,
"ñ": 106,
"ò": 107,
"ó": 108,
"ô": 109,
"õ": 110,
"ö": 111,
"ø": 112,
"ù": 113,
"ú": 114,
"û": 115,
"ü": 116,
"ý": 117,
"þ": 118,
"ÿ": 119,
"Ā": 120,
"ā": 121,
"Ă": 122,
"ă": 123,
"Ą": 124,
"ą": 125,
"Ć": 126,
"ć": 127,
"Ĉ": 128,
"ĉ": 129,
"Č": 130,
"č": 131,
"ď": 132,
"Đ": 133,
"đ": 134,
"Ē": 135,
"ē": 136,
"Ĕ": 137,
"ĕ": 138,
"Ė": 139,
"ė": 140,
"Ę": 141,
"ę": 142,
"Ě": 143,
"ě": 144,
"Ĝ": 145,
"ĝ": 146,
"Ğ": 147,
"ğ": 148,
"ġ": 149,
"ģ": 150,
"Ĥ": 151,
"ĥ": 152,
"Ħ": 153,
"ħ": 154,
"ĩ": 155,
"Ī": 156,
"ī": 157,
"ĭ": 158,
"į": 159,
"İ": 160,
"ı": 161,
"ĵ": 162,
"Ķ": 163,
"ķ": 164,
"ĺ": 165,
"Ļ": 166,
"ļ": 167,
"Ľ": 168,
"ľ": 169,
"Ł": 170,
"ł": 171,
"Ń": 172,
"ń": 173,
"ņ": 174,
"ň": 175,
"ŋ": 176,
"Ō": 177,
"ō": 178,
"ŏ": 179,
"Ő": 180,
"ő": 181,
"Œ": 182,
"œ": 183,
"ŕ": 184,
"ŗ": 185,
"Ř": 186,
"ř": 187,
"Ś": 188,
"ś": 189,
"Ŝ": 190,
"ŝ": 191,
"Ş": 192,
"ş": 193,
"Š": 194,
"š": 195,
"Ţ": 196,
"ţ": 197,
"Ť": 198,
"ť": 199,
"Ŧ": 200,
"ũ": 201,
"Ū": 202,
"ū": 203,
"ŭ": 204,
"ů": 205,
"ű": 206,
"ų": 207,
"ŵ": 208,
"ŷ": 209,
"Ÿ": 210,
"Ź": 211,
"ź": 212,
"Ż": 213,
"ż": 214,
"Ž": 215,
"ž": 216,
"Ƅ": 217,
"Ƌ": 218,
"ƌ": 219,
"Ǝ": 220,
"Ə": 221,
"ƒ": 222,
"ơ": 223,
"ư": 224,
"ƿ": 225,
"ǁ": 226,
"ǂ": 227,
"ǃ": 228,
"ǎ": 229,
"ǐ": 230,
"ǒ": 231,
"ǔ": 232,
"ǚ": 233,
"ǝ": 234,
"ǣ": 235,
"Ǧ": 236,
"ǧ": 237,
"ǩ": 238,
"ǫ": 239,
"ǵ": 240,
"ǹ": 241,
"ȁ": 242,
"ȃ": 243,
"Ș": 244,
"ș": 245,
"Ț": 246,
"ț": 247,
"Ȝ": 248,
"ȝ": 249,
"ȧ": 250,
"Ɂ": 251,
"ɂ": 252,
"ɐ": 253,
"ɑ": 254,
"ɒ": 255,
"ɔ": 256,
"ɕ": 257,
"ɖ": 258,
"ɗ": 259,
"ɘ": 260,
"ə": 261,
"ɛ": 262,
"ɜ": 263,
"ɝ": 264,
"ɟ": 265,
"ɡ": 266,
"ɣ": 267,
"ɥ": 268,
"ɦ": 269,
"ɨ": 270,
"ɩ": 271,
"ɪ": 272,
"ɫ": 273,
"ɮ": 274,
"ɯ": 275,
"ɲ": 276,
"ɳ": 277,
"ɶ": 278,
"ɷ": 279,
"ɸ": 280,
"ɹ": 281,
"ɺ": 282,
"ɾ": 283,
"ʁ": 284,
"ʂ": 285,
"ʃ": 286,
"ʇ": 287,
"ʈ": 288,
"ʊ": 289,
"ʋ": 290,
"ʌ": 291,
"ʎ": 292,
"ʏ": 293,
"ʐ": 294,
"ʑ": 295,
"ʒ": 296,
"ʔ": 297,
"ʕ": 298,
"ʘ": 299,
"ʙ": 300,
"ʝ": 301,
"ʟ": 302,
"ʧ": 303,
"ʹ": 304,
"ʻ": 305,
"ʼ": 306,
"ʽ": 307,
"ʾ": 308,
"ʿ": 309,
"ˀ": 310,
"ˆ": 311,
"ˇ": 312,
"ˈ": 313,
"ˊ": 314,
"ˋ": 315,
"ˌ": 316,
"ː": 317,
"Α": 318,
"Β": 319,
"Ε": 320,
"Η": 321,
"Τ": 322,
"Υ": 323,
"ν": 324,
"ο": 325,
"Ј": 326,
"М": 327,
"а": 328,
"б": 329,
"й": 330,
"к": 331,
"о": 332,
"с": 333,
"у": 334,
"ш": 335,
"я": 336,
"ـ": 337,
"ආ": 338,
"ජ": 339,
"බ": 340,
"ය": 341,
"ව": 342,
"ḋ": 343,
"Ḍ": 344,
"ḍ": 345,
"ḏ": 346,
"ḗ": 347,
"Ḡ": 348,
"Ḥ": 349,
"ḥ": 350,
"Ḩ": 351,
"ḫ": 352,
"ḱ": 353,
"ḵ": 354,
"ḷ": 355,
"ḻ": 356,
"ḿ": 357,
"ṁ": 358,
"Ṃ": 359,
"ṃ": 360,
"ṅ": 361,
"ṇ": 362,
"ṉ": 363,
"ṓ": 364,
"ṗ": 365,
"ṙ": 366,
"ṛ": 367,
"ṟ": 368,
"Ṣ": 369,
"ṣ": 370,
"ṫ": 371,
"Ṭ": 372,
"ṭ": 373,
"Ṯ": 374,
"ṯ": 375,
"Ṳ": 376,
"ṹ": 377,
"ẏ": 378,
"Ẓ": 379,
"ẓ": 380,
"ẞ": 381,
"ạ": 382,
"ả": 383,
"ấ": 384,
"ầ": 385,
"ẩ": 386,
"ậ": 387,
"ắ": 388,
"ằ": 389,
"ẵ": 390,
"ặ": 391,
"Ẹ": 392,
"ẹ": 393,
"ẻ": 394,
"ẽ": 395,
"Ế": 396,
"ế": 397,
"ề": 398,
"ể": 399,
"ễ": 400,
"ệ": 401,
"ỉ": 402,
"ị": 403,
"Ọ": 404,
"ọ": 405,
"ỏ": 406,
"ố": 407,
"ồ": 408,
"ổ": 409,
"ỗ": 410,
"ộ": 411,
"ớ": 412,
"ờ": 413,
"ở": 414,
"ợ": 415,
"ụ": 416,
"ủ": 417,
"ứ": 418,
"ử": 419,
"ữ": 420,
"ự": 421,
"ỳ": 422,
"ỹ": 423,
"ⱡ": 424,
"ー": 425,
"Ꜧ": 426,
"ꜧ": 427,
"ꞌ": 428,
"ꞯ": 429,
"fl": 430,
"0": 431,
"1": 432,
"2": 433,
"3": 434,
"4": 435,
"5": 436,
"6": 437,
"7": 438,
"8": 439,
"9": 440,
"³": 441,
"¹": 442,
"١": 443,
"٢": 444,
"٤": 445,
"٥": 446,
"٦": 447,
"٧": 448,
"٨": 449,
"٩": 450,
"۰": 451,
"०": 452,
"१": 453,
"२": 454,
"३": 455,
"४": 456,
"५": 457,
"६": 458,
"७": 459,
"८": 460,
"९": 461,
"၀": 462,
"၁": 463,
"၂": 464,
"၃": 465,
"၄": 466,
"၅": 467,
"၆": 468,
"၇": 469,
"၈": 470,
"၉": 471,
"០": 472,
"១": 473,
"២": 474,
"៣": 475,
"៤": 476,
"៥": 477,
"៦": 478,
"៧": 479,
"៨": 480,
"៩": 481,
"\t": 482,
" ": 483,
"!": 484,
"\"": 485,
"#": 486,
"$": 487,
"%": 488,
"&": 489,
"'": 490,
"(": 491,
")": 492,
"*": 493,
"+": 494,
",": 495,
"-": 496,
".": 497,
"/": 498,
":": 499,
";": 500,
"<": 501,
"=": 502,
">": 503,
"?": 504,
"@": 505,
"[": 506,
"\\": 507,
"]": 508,
"^": 509,
"_": 510,
"`": 511,
"{": 512,
"|": 513,
"}": 514,
"~": 515,
"": 516,
"€": 517,
"": 518,
"‚": 519,
"ƒ": 520,
"ˆ": 521,
"‰": 522,
"Š": 523,
"‹": 524,
"Œ": 525,
"": 526,
"Ž": 527,
"": 528,
"": 529,
"’": 530,
"“": 531,
"”": 532,
"•": 533,
"–": 534,
"—": 535,
"˜": 536,
"™": 537,
"š": 538,
"œ": 539,
"": 540,
"ž": 541,
"¡": 542,
"¢": 543,
"£": 544,
"¤": 545,
"¥": 546,
"¦": 547,
"§": 548,
"¨": 549,
"©": 550,
"«": 551,
"¬": 552,
"­": 553,
"®": 554,
"°": 555,
"±": 556,
"´": 557,
"¶": 558,
"·": 559,
"»": 560,
"½": 561,
"¿": 562,
"×": 563,
"÷": 564,
"˥": 565,
"˦": 566,
"˧": 567,
"˩": 568,
"̶": 569,
"־": 570,
"״": 571,
"،": 572,
"؟": 573,
"۞": 574,
"।": 575,
"॥": 576,
"ා": 577,
"ු": 578,
"ේ": 579,
"ෝ": 580,
"་": 581,
"།": 582,
" ": 583,
"᚛": 584,
"᚜": 585,
"​": 586,
"‌": 587,
"‍": 588,
"‎": 589,
"‏": 590,
"‐": 591,
"–": 592,
"—": 593,
"―": 594,
"‖": 595,
"‘": 596,
"’": 597,
"‚": 598,
"“": 599,
"”": 600,
"„": 601,
"†": 602,
"‡": 603,
"•": 604,
"‬": 605,
"‭": 606,
"‰": 607,
"′": 608,
"※": 609,
"‿": 610,
"⁂": 611,
"⁄": 612,
"⁎": 613,
"⁠": 614,
"⁣": 615,
"₡": 616,
"₣": 617,
"₤": 618,
"₩": 619,
"€": 620,
"₱": 621,
"₵": 622,
"₹": 623,
"₿": 624,
"™": 625,
"↊": 626,
"↋": 627,
"←": 628,
"↑": 629,
"→": 630,
"↗": 631,
"↫": 632,
"∂": 633,
"∆": 634,
"∇": 635,
"∈": 636,
"∉": 637,
"−": 638,
"∗": 639,
"∘": 640,
"∙": 641,
"√": 642,
"∝": 643,
"∞": 644,
"∴": 645,
"∼": 646,
"≈": 647,
"≒": 648,
"≠": 649,
"≡": 650,
"≤": 651,
"≥": 652,
"⊙": 653,
"⋅": 654,
"⌈": 655,
"⌉": 656,
"⌊": 657,
"⌋": 658,
"─": 659,
"█": 660,
"▔": 661,
"▼": 662,
"◉": 663,
"◊": 664,
"○": 665,
"●": 666,
"☃": 667,
"★": 668,
"☆": 669,
"☉": 670,
"☐": 671,
"☚": 672,
"☛": 673,
"☣": 674,
"☭": 675,
"☯": 676,
"☺": 677,
"☻": 678,
"♄": 679,
"♑": 680,
"♒": 681,
"♠": 682,
"♡": 683,
"♣": 684,
"♥": 685,
"♦": 686,
"♪": 687,
"♫": 688,
"♭": 689,
"♮": 690,
"♯": 691,
"✅": 692,
"✙": 693,
"✚": 694,
"✡": 695,
"✿": 696,
"❌": 697,
"❤": 698,
"❦": 699,
"⟨": 700,
"⟩": 701,
"⬄": 702,
"⬱": 703,
"⿰": 704,
"⿱": 705,
"⿺": 706,
"、": 707,
"。": 708,
"〉": 709,
"《": 710,
"》": 711,
"「": 712,
"」": 713,
"『": 714,
"』": 715,
"〜": 716,
"・": 717,
"꞉": 718,
"": 719,
"": 720,
"": 721,
"": 722,
"!": 723,
"�": 724,
"𝄆": 725,
"𝄇": 726,
"🆖": 727,
"🏰": 728,
"🏴": 729,
"👫": 730,
"👽": 731,
"😊": 732,
"😝": 733,
"🜨": 734,
"󠁢": 735,
"󠁧": 736,
"󠁬": 737,
"󠁳": 738,
"󠁷": 739,
"󠁿": 740,
"􏿾": 741
}