diff --git a/.gitattributes b/.gitattributes index 7fa96b2..7a0b41a 100644 --- a/.gitattributes +++ b/.gitattributes @@ -49,3 +49,5 @@ s3gen.safetensors filter=lfs diff=lfs merge=lfs -text t3_cfg.safetensors filter=lfs diff=lfs merge=lfs -text Cangjie5_TC.json filter=lfs diff=lfs merge=lfs -text + +t3_mtl23ls_v2.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/grapheme_mtl_merged_expanded_v1.json b/grapheme_mtl_merged_expanded_v1.json new file mode 100644 index 0000000..4b0e465 --- /dev/null +++ b/grapheme_mtl_merged_expanded_v1.json @@ -0,0 +1,3806 @@ +{ + "version": "1.0", + "truncation": null, + "padding": null, + "added_tokens": [ + { + "id": 0, + "special": true, + "content": "[STOP]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + }, + { + "id": 1, + "special": true, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + }, + { + "id": 2, + "special": true, + "content": "[SPACE]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + }, + { + "id": 255, + "special": true, + "content": "[START]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + }, + { + "id": 604, + "content": "[UH]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 605, + "content": "[UM]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 606, + "content": "[giggle]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 607, + "content": "[laughter]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 608, + "content": "[guffaw]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 609, + "content": "[inhale]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 610, + "content": "[exhale]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 611, + "content": "[sigh]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 612, + "content": "[cry]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 613, + "content": "[bark]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 614, + "content": "[howl]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 615, + "content": "[meow]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 616, + "content": "[singing]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 617, + "content": "[music]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 618, + "content": "[whistle]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 619, + "content": "[humming]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 620, + "content": "[gasp]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 621, + "content": "[groan]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 622, + "content": "[whisper]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 623, + "content": "[mumble]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 624, + "content": "[sniff]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 625, + "content": "[sneeze]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 626, + "content": "[cough]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 627, + "content": "[snore]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 628, + "content": "[chew]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 629, + "content": "[sip]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 630, + "content": "[clear_throat]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 631, + "content": "[kiss]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 632, + "content": "[shhh]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 633, + "content": "[gibberish]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 634, + "content": "[fr]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 635, + "content": "[es]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 636, + "content": "[de]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 637, + "content": "[it]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 638, + "content": "[ipa]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 639, + "content": "[end_of_label]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 695, + "content": "[PLACEHOLDER55]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 696, + "content": "[PLACEHOLDER56]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 697, + "content": "[PLACEHOLDER57]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 698, + "content": "[PLACEHOLDER58]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 699, + "content": "[PLACEHOLDER59]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 700, + "content": "[PLACEHOLDER60]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 701, + "content": "[PLACEHOLDER61]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 702, + "content": "[PLACEHOLDER62]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 703, + "content": "[PLACEHOLDER63]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 704, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 705, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 706, + "content": "[SEP]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 707, + "content": "[CLS]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 708, + "content": "[en]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 709, + "content": "[nl]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 710, + "content": "[pt]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 711, + "content": "[el]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 712, + "content": "[tr]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 713, + "content": "[sv]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 714, + "content": "[no]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 715, + "content": "[da]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 716, + "content": "[ru]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 717, + "content": "[pl]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 718, + "content": "[sk]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 719, + "content": "[cs]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 720, + "content": "[hu]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 721, + "content": "[ar]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 722, + "content": "[hi]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 723, + "content": "[ja]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 724, + "content": "[ko]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 725, + "content": "[zh]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 726, + "content": "[ro]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 727, + "content": "[bg]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 729, + "content": "[ea]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 730, + "content": "[sw]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 732, + "content": "[vi]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 733, + "content": "[cj_a]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 734, + "content": "[cj_b]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 735, + "content": "[cj_c]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 736, + "content": "[cj_d]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 737, + "content": "[cj_e]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 738, + "content": "[cj_f]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 739, + "content": "[cj_g]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 740, + "content": "[cj_h]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 741, + "content": "[cj_i]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 742, + "content": "[cj_j]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 743, + "content": "[cj_k]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 744, + "content": "[cj_l]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 745, + "content": "[cj_m]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 746, + "content": "[cj_n]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 747, + "content": "[cj_o]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 748, + "content": "[cj_p]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 749, + "content": "[cj_q]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 750, + "content": "[cj_r]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 751, + "content": "[cj_s]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 752, + "content": "[cj_t]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 753, + "content": "[cj_u]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 754, + "content": "[cj_v]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 755, + "content": "[cj_w]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 756, + "content": "[cj_x]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 757, + "content": "[cj_y]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 758, + "content": "[cj_z]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 759, + "content": "[cj_0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 760, + "content": "[cj_1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 761, + "content": "[cj_2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2052, + "content": "[cj_3]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2053, + "content": "[cj_4]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2059, + "content": "[cj_5]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2060, + "content": "[cj_6]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2061, + "content": "[cj_7]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2062, + "content": "[cj_8]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2063, + "content": "[cj_9]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2064, + "content": "[cj_.]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2065, + "content": "[PLACEHOLDER45]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2107, + "content": "[fi]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 2108, + "content": "[ta]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 2109, + "content": "[ms]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + { + "id": 2110, + "content": "[he]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": null, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "vocab": { + "[STOP]": 0, + "[UNK]": 1, + "[SPACE]": 2, + "!": 3, + "'": 4, + "(": 5, + ")": 6, + ",": 7, + "-": 8, + ".": 9, + "/": 10, + ":": 11, + ";": 12, + "?": 13, + "a": 14, + "b": 15, + "c": 16, + "d": 17, + "e": 18, + "f": 19, + "g": 20, + "h": 21, + "i": 22, + "j": 23, + "k": 24, + "l": 25, + "m": 26, + "n": 27, + "o": 28, + "p": 29, + "q": 30, + "r": 31, + "s": 32, + "t": 33, + "u": 34, + "v": 35, + "w": 36, + "x": 37, + "y": 38, + "z": 39, + "th": 40, + "in": 41, + "the": 42, + "an": 43, + "er": 44, + "ou": 45, + "re": 46, + "on": 47, + "at": 48, + "ed": 49, + "en": 50, + "to": 51, + "ing": 52, + "and": 53, + "is": 54, + "as": 55, + "al": 56, + "or": 57, + "of": 58, + "ar": 59, + "it": 60, + "es": 61, + "he": 62, + "st": 63, + "le": 64, + "om": 65, + "se": 66, + "be": 67, + "ad": 68, + "ow": 69, + "ly": 70, + "ch": 71, + "wh": 72, + "that": 73, + "you": 74, + "li": 75, + "ve": 76, + "ac": 77, + "ti": 78, + "ld": 79, + "me": 80, + "was": 81, + "gh": 82, + "id": 83, + "ll": 84, + "wi": 85, + "ent": 86, + "for": 87, + "ay": 88, + "ro": 89, + "ver": 90, + "ic": 91, + "her": 92, + "ke": 93, + "his": 94, + "no": 95, + "ut": 96, + "un": 97, + "ir": 98, + "lo": 99, + "we": 100, + "ri": 101, + "ha": 102, + "with": 103, + "ght": 104, + "out": 105, + "im": 106, + "ion": 107, + "all": 108, + "ab": 109, + "one": 110, + "ne": 111, + "ge": 112, + "ould": 113, + "ter": 114, + "mo": 115, + "had": 116, + "ce": 117, + "she": 118, + "go": 119, + "sh": 120, + "ur": 121, + "am": 122, + "so": 123, + "pe": 124, + "my": 125, + "de": 126, + "are": 127, + "but": 128, + "ome": 129, + "fr": 130, + "ther": 131, + "fe": 132, + "su": 133, + "do": 134, + "con": 135, + "te": 136, + "ain": 137, + "ere": 138, + "po": 139, + "if": 140, + "they": 141, + "us": 142, + "ag": 143, + "tr": 144, + "now": 145, + "oun": 146, + "this": 147, + "have": 148, + "not": 149, + "sa": 150, + "il": 151, + "up": 152, + "thing": 153, + "from": 154, + "ap": 155, + "him": 156, + "ack": 157, + "ation": 158, + "ant": 159, + "our": 160, + "op": 161, + "like": 162, + "ust": 163, + "ess": 164, + "bo": 165, + "ok": 166, + "ul": 167, + "ind": 168, + "ex": 169, + "com": 170, + "some": 171, + "there": 172, + "ers": 173, + "co": 174, + "res": 175, + "man": 176, + "ard": 177, + "pl": 178, + "wor": 179, + "way": 180, + "tion": 181, + "fo": 182, + "ca": 183, + "were": 184, + "by": 185, + "ate": 186, + "pro": 187, + "ted": 188, + "ound": 189, + "own": 190, + "would": 191, + "ts": 192, + "what": 193, + "qu": 194, + "ally": 195, + "ight": 196, + "ck": 197, + "gr": 198, + "when": 199, + "ven": 200, + "can": 201, + "ough": 202, + "ine": 203, + "end": 204, + "per": 205, + "ous": 206, + "od": 207, + "ide": 208, + "know": 209, + "ty": 210, + "very": 211, + "si": 212, + "ak": 213, + "who": 214, + "about": 215, + "ill": 216, + "them": 217, + "est": 218, + "red": 219, + "ye": 220, + "could": 221, + "ong": 222, + "your": 223, + "their": 224, + "em": 225, + "just": 226, + "other": 227, + "into": 228, + "any": 229, + "whi": 230, + "um": 231, + "tw": 232, + "ast": 233, + "der": 234, + "did": 235, + "ie": 236, + "been": 237, + "ace": 238, + "ink": 239, + "ity": 240, + "back": 241, + "ting": 242, + "br": 243, + "more": 244, + "ake": 245, + "pp": 246, + "then": 247, + "sp": 248, + "el": 249, + "use": 250, + "bl": 251, + "said": 252, + "over": 253, + "get": 254, + "[START]": 255, + "\"": 256, + "#": 257, + "$": 258, + "%": 259, + "&": 260, + "*": 261, + "+": 262, + "0": 263, + "1": 264, + "2": 265, + "3": 266, + "4": 267, + "5": 268, + "6": 269, + "7": 270, + "8": 271, + "9": 272, + "<": 273, + "=": 274, + ">": 275, + "@": 276, + "A": 277, + "B": 278, + "C": 279, + "D": 280, + "E": 281, + "F": 282, + "G": 283, + "H": 284, + "I": 285, + "J": 286, + "K": 287, + "L": 288, + "M": 289, + "N": 290, + "O": 291, + "P": 292, + "Q": 293, + "R": 294, + "S": 295, + "T": 296, + "U": 297, + "V": 298, + "W": 299, + "X": 300, + "Y": 301, + "Z": 302, + "[": 303, + "\\": 304, + "]": 305, + "^": 306, + "_": 307, + "`": 308, + "{": 309, + "|": 310, + "}": 311, + "~": 312, + "‐": 313, + "‑": 314, + "‒": 315, + "–": 316, + "—": 317, + "―": 318, + "‖": 319, + "‗": 320, + "‘": 321, + "’": 322, + "‚": 323, + "‛": 324, + "“": 325, + "”": 326, + "„": 327, + "‟": 328, + " ": 329, + "¡": 330, + "¢": 331, + "£": 332, + "¤": 333, + "¥": 334, + "¦": 335, + "§": 336, + "¨": 337, + "©": 338, + "ª": 339, + "«": 340, + "¬": 341, + "­": 342, + "®": 343, + "¯": 344, + "°": 345, + "±": 346, + "²": 347, + "³": 348, + "´": 349, + "µ": 350, + "¶": 351, + "·": 352, + "¸": 353, + "¹": 354, + "º": 355, + "»": 356, + "¼": 357, + "½": 358, + "¾": 359, + "¿": 360, + "À": 361, + "Á": 362, + "Â": 363, + "Ã": 364, + "Ä": 365, + "Å": 366, + "Æ": 367, + "Ç": 368, + "È": 369, + "É": 370, + "Ê": 371, + "Ë": 372, + "Ì": 373, + "Í": 374, + "Î": 375, + "Ï": 376, + "Ð": 377, + "Ñ": 378, + "Ò": 379, + "Ó": 380, + "Ô": 381, + "Õ": 382, + "Ö": 383, + "×": 384, + "Ø": 385, + "Ù": 386, + "Ú": 387, + "Û": 388, + "Ü": 389, + "Ý": 390, + "Þ": 391, + "ß": 392, + "à": 393, + "á": 394, + "â": 395, + "ã": 396, + "ä": 397, + "å": 398, + "æ": 399, + "ç": 400, + "è": 401, + "é": 402, + "ê": 403, + "ë": 404, + "ì": 405, + "í": 406, + "î": 407, + "ï": 408, + "ð": 409, + "ñ": 410, + "ò": 411, + "ó": 412, + "ô": 413, + "õ": 414, + "ö": 415, + "÷": 416, + "ø": 417, + "ù": 418, + "ú": 419, + "û": 420, + "ü": 421, + "ý": 422, + "þ": 423, + "ÿ": 424, + "ɐ": 425, + "ɑ": 426, + "ɒ": 427, + "ɓ": 428, + "ɔ": 429, + "ɕ": 430, + "ɖ": 431, + "ɗ": 432, + "ɘ": 433, + "ə": 434, + "ɚ": 435, + "ɛ": 436, + "ɜ": 437, + "ɝ": 438, + "ɞ": 439, + "ɟ": 440, + "ɠ": 441, + "ɡ": 442, + "ɢ": 443, + "ɣ": 444, + "ɤ": 445, + "ɥ": 446, + "ɦ": 447, + "ɧ": 448, + "ɨ": 449, + "ɩ": 450, + "ɪ": 451, + "ɫ": 452, + "ɬ": 453, + "ɭ": 454, + "ɮ": 455, + "ɯ": 456, + "ɰ": 457, + "ɱ": 458, + "ɲ": 459, + "ɳ": 460, + "ɴ": 461, + "ɵ": 462, + "ɶ": 463, + "ɷ": 464, + "ɸ": 465, + "ɹ": 466, + "ɺ": 467, + "ɻ": 468, + "ɼ": 469, + "ɽ": 470, + "ɾ": 471, + "ɿ": 472, + "ʀ": 473, + "ʁ": 474, + "ʂ": 475, + "ʃ": 476, + "ʄ": 477, + "ʅ": 478, + "ʆ": 479, + "ʇ": 480, + "ʈ": 481, + "ʉ": 482, + "ʊ": 483, + "ʋ": 484, + "ʌ": 485, + "ʍ": 486, + "ʎ": 487, + "ʏ": 488, + "ʐ": 489, + "ʑ": 490, + "ʒ": 491, + "ʓ": 492, + "ʔ": 493, + "ʕ": 494, + "ʖ": 495, + "ʗ": 496, + "ʘ": 497, + "ʙ": 498, + "ʚ": 499, + "ʛ": 500, + "ʜ": 501, + "ʝ": 502, + "ʞ": 503, + "ʟ": 504, + "ʠ": 505, + "ʡ": 506, + "ʢ": 507, + "ʣ": 508, + "ʤ": 509, + "ʥ": 510, + "ʦ": 511, + "ʧ": 512, + "ʨ": 513, + "ʩ": 514, + "ʪ": 515, + "ʫ": 516, + "ʬ": 517, + "ʭ": 518, + "ʮ": 519, + "ʯ": 520, + "ʰ": 521, + "ʱ": 522, + "ʲ": 523, + "ʳ": 524, + "ʴ": 525, + "ʵ": 526, + "ʶ": 527, + "ʷ": 528, + "ʸ": 529, + "ʹ": 530, + "ʺ": 531, + "ʻ": 532, + "ʼ": 533, + "ʽ": 534, + "ʾ": 535, + "ʿ": 536, + "ˀ": 537, + "ˁ": 538, + "˂": 539, + "˃": 540, + "˄": 541, + "˅": 542, + "ˆ": 543, + "ˇ": 544, + "ˈ": 545, + "ˉ": 546, + "ˊ": 547, + "ˋ": 548, + "ˌ": 549, + "ˍ": 550, + "ˎ": 551, + "ˏ": 552, + "ː": 553, + "ˑ": 554, + "˒": 555, + "˓": 556, + "˔": 557, + "˕": 558, + "˖": 559, + "˗": 560, + "˘": 561, + "˙": 562, + "˚": 563, + "˛": 564, + "˜": 565, + "˝": 566, + "˞": 567, + "˟": 568, + "ˠ": 569, + "ˡ": 570, + "ˢ": 571, + "ˣ": 572, + "ˤ": 573, + "˥": 574, + "˦": 575, + "˧": 576, + "˨": 577, + "˩": 578, + "˪": 579, + "˫": 580, + "ˬ": 581, + "˭": 582, + "ˮ": 583, + "˯": 584, + "˰": 585, + "˱": 586, + "˲": 587, + "˳": 588, + "˴": 589, + "˵": 590, + "˶": 591, + "˷": 592, + "˸": 593, + "˹": 594, + "˺": 595, + "˻": 596, + "˼": 597, + "˽": 598, + "˾": 599, + "˿": 600, + "ā": 601, + "ō": 602, + "…": 603, + "[UH]": 604, + "[UM]": 605, + "[giggle]": 606, + "[laughter]": 607, + "[guffaw]": 608, + "[inhale]": 609, + "[exhale]": 610, + "[sigh]": 611, + "[cry]": 612, + "[bark]": 613, + "[howl]": 614, + "[meow]": 615, + "[singing]": 616, + "[music]": 617, + "[whistle]": 618, + "[humming]": 619, + "[gasp]": 620, + "[groan]": 621, + "[whisper]": 622, + "[mumble]": 623, + "[sniff]": 624, + "[sneeze]": 625, + "[cough]": 626, + "[snore]": 627, + "[chew]": 628, + "[sip]": 629, + "[clear_throat]": 630, + "[kiss]": 631, + "[shhh]": 632, + "[gibberish]": 633, + "[fr]": 634, + "[es]": 635, + "[de]": 636, + "[it]": 637, + "[ipa]": 638, + "[end_of_label]": 639, + "ŋ": 640, + "ᵻ": 641, + "θ": 642, + "̩": 643, + "̃": 644, + "ɑː": 645, + "iː": 646, + "uː": 647, + "ɜː": 648, + "ɔː": 649, + "oː": 650, + "eɪ": 651, + "oʊ": 652, + "aɪ": 653, + "aʊ": 654, + "ɔɪ": 655, + "dʒ": 656, + "tʃ": 657, + "ɪŋ": 658, + "ᵻd": 659, + "ˈiː": 660, + "ˌiː": 661, + "ˈɪ": 662, + "ˌɪ": 663, + "ˈeɪ": 664, + "ˌeɪ": 665, + "ˈɛ": 666, + "ˌɛ": 667, + "ˈæ": 668, + "ˌæ": 669, + "ˈɑː": 670, + "ˌɑː": 671, + "ˈɔː": 672, + "ˌɔː": 673, + "oːɹ": 674, + "ˈoːɹ": 675, + "ˌoːɹ": 676, + "ˈoʊ": 677, + "ˌoʊ": 678, + "ˈʊ": 679, + "ˌʊ": 680, + "ˈuː": 681, + "ˌuː": 682, + "ˈɜː": 683, + "ˌɜː": 684, + "ˈʌ": 685, + "ˌʌ": 686, + "ˈaɪ": 687, + "ˌaɪ": 688, + "ˈaʊ": 689, + "ˌaʊ": 690, + "ˈɔɪ": 691, + "ˌɔɪ": 692, + "ˈɚ": 693, + "ˌɐ": 694, + "[PLACEHOLDER55]": 695, + "[PLACEHOLDER56]": 696, + "[PLACEHOLDER57]": 697, + "[PLACEHOLDER58]": 698, + "[PLACEHOLDER59]": 699, + "[PLACEHOLDER60]": 700, + "[PLACEHOLDER61]": 701, + "[PLACEHOLDER62]": 702, + "[PLACEHOLDER63]": 703, + "[MASK]": 704, + "[PAD]": 705, + "[SEP]": 706, + "[CLS]": 707, + "[en]": 708, + "[nl]": 709, + "[pt]": 710, + "[el]": 711, + "[tr]": 712, + "[sv]": 713, + "[no]": 714, + "[da]": 715, + "[ru]": 716, + "[pl]": 717, + "[sk]": 718, + "[cs]": 719, + "[hu]": 720, + "[ar]": 721, + "[hi]": 722, + "[ja]": 723, + "[ko]": 724, + "[zh]": 725, + "[ro]": 726, + "[bg]": 727, + " ": 728, + "[ea]": 729, + "[sw]": 730, + "─": 731, + "[vi]": 732, + "[cj_a]": 733, + "[cj_b]": 734, + "[cj_c]": 735, + "[cj_d]": 736, + "[cj_e]": 737, + "[cj_f]": 738, + "[cj_g]": 739, + "[cj_h]": 740, + "[cj_i]": 741, + "[cj_j]": 742, + "[cj_k]": 743, + "[cj_l]": 744, + "[cj_m]": 745, + "[cj_n]": 746, + "[cj_o]": 747, + "[cj_p]": 748, + "[cj_q]": 749, + "[cj_r]": 750, + "[cj_s]": 751, + "[cj_t]": 752, + "[cj_u]": 753, + "[cj_v]": 754, + "[cj_w]": 755, + "[cj_x]": 756, + "[cj_y]": 757, + "[cj_z]": 758, + "[cj_0]": 759, + "[cj_1]": 760, + "[cj_2]": 761, + "̈": 762, + "̄": 763, + "́": 764, + "μ": 765, + "̧": 766, + "⁄": 767, + "̀": 768, + "̂": 769, + "̊": 770, + "̆": 771, + "̨": 772, + "̇": 773, + "̌": 774, + "Đ": 775, + "đ": 776, + "Ħ": 777, + "ħ": 778, + "ı": 779, + "ĸ": 780, + "Ł": 781, + "ł": 782, + "Ŋ": 783, + "̋": 784, + "Œ": 785, + "œ": 786, + "Ŧ": 787, + "ŧ": 788, + "ƀ": 789, + "Ɓ": 790, + "Ƃ": 791, + "ƃ": 792, + "Ƅ": 793, + "ƅ": 794, + "Ɔ": 795, + "Ƈ": 796, + "ƈ": 797, + "Ɖ": 798, + "Ɗ": 799, + "Ƌ": 800, + "ƌ": 801, + "ƍ": 802, + "Ǝ": 803, + "Ə": 804, + "Ɛ": 805, + "Ƒ": 806, + "ƒ": 807, + "Ɠ": 808, + "Ɣ": 809, + "ƕ": 810, + "Ɩ": 811, + "Ɨ": 812, + "Ƙ": 813, + "ƙ": 814, + "ƚ": 815, + "ƛ": 816, + "Ɯ": 817, + "Ɲ": 818, + "ƞ": 819, + "Ɵ": 820, + "̛": 821, + "Ƣ": 822, + "ƣ": 823, + "Ƥ": 824, + "ƥ": 825, + "Ʀ": 826, + "Ƨ": 827, + "ƨ": 828, + "Ʃ": 829, + "ƪ": 830, + "ƫ": 831, + "Ƭ": 832, + "ƭ": 833, + "Ʈ": 834, + "Ʊ": 835, + "Ʋ": 836, + "Ƴ": 837, + "ƴ": 838, + "Ƶ": 839, + "ƶ": 840, + "Ʒ": 841, + "Ƹ": 842, + "ƹ": 843, + "ƺ": 844, + "ƻ": 845, + "Ƽ": 846, + "ƽ": 847, + "ƾ": 848, + "ƿ": 849, + "ǀ": 850, + "ǁ": 851, + "ǂ": 852, + "ǃ": 853, + "ǝ": 854, + "Ǥ": 855, + "ǥ": 856, + "Ƕ": 857, + "Ƿ": 858, + "̏": 859, + "̑": 860, + "̦": 861, + "Ȝ": 862, + "ȝ": 863, + "Ƞ": 864, + "ȡ": 865, + "Ȣ": 866, + "ȣ": 867, + "Ȥ": 868, + "ȥ": 869, + "ȴ": 870, + "ȵ": 871, + "ȶ": 872, + "ȷ": 873, + "ȸ": 874, + "ȹ": 875, + "Ⱥ": 876, + "Ȼ": 877, + "ȼ": 878, + "Ƚ": 879, + "Ⱦ": 880, + "ȿ": 881, + "ɀ": 882, + "Ɂ": 883, + "ɂ": 884, + "Ƀ": 885, + "Ʉ": 886, + "Ʌ": 887, + "Ɇ": 888, + "ɇ": 889, + "Ɉ": 890, + "ɉ": 891, + "Ɋ": 892, + "ɋ": 893, + "Ɍ": 894, + "ɍ": 895, + "Ɏ": 896, + "ɏ": 897, + "̅": 898, + "̉": 899, + "̍": 900, + "̎": 901, + "̐": 902, + "̒": 903, + "̓": 904, + "̔": 905, + "̕": 906, + "̖": 907, + "̗": 908, + "̘": 909, + "̙": 910, + "̚": 911, + "̜": 912, + "̝": 913, + "̞": 914, + "̟": 915, + "̠": 916, + "̡": 917, + "̢": 918, + "̣": 919, + "̤": 920, + "̥": 921, + "̪": 922, + "̫": 923, + "̬": 924, + "̭": 925, + "̮": 926, + "̯": 927, + "̰": 928, + "̱": 929, + "̲": 930, + "̳": 931, + "̴": 932, + "̵": 933, + "̶": 934, + "̷": 935, + "̸": 936, + "̹": 937, + "̺": 938, + "̻": 939, + "̼": 940, + "̽": 941, + "̾": 942, + "̿": 943, + "͂": 944, + "ͅ": 945, + "͆": 946, + "͇": 947, + "͈": 948, + "͉": 949, + "͊": 950, + "͋": 951, + "͌": 952, + "͍": 953, + "͎": 954, + "͏": 955, + "͐": 956, + "͑": 957, + "͒": 958, + "͓": 959, + "͔": 960, + "͕": 961, + "͖": 962, + "͗": 963, + "͘": 964, + "͙": 965, + "͚": 966, + "͛": 967, + "͜": 968, + "͝": 969, + "͞": 970, + "͟": 971, + "͠": 972, + "͡": 973, + "͢": 974, + "ͣ": 975, + "ͤ": 976, + "ͥ": 977, + "ͦ": 978, + "ͧ": 979, + "ͨ": 980, + "ͩ": 981, + "ͪ": 982, + "ͫ": 983, + "ͬ": 984, + "ͭ": 985, + "ͮ": 986, + "ͯ": 987, + "Ͱ": 988, + "ͱ": 989, + "Ͳ": 990, + "ͳ": 991, + "͵": 992, + "Ͷ": 993, + "ͷ": 994, + "ͻ": 995, + "ͼ": 996, + "ͽ": 997, + "Ϳ": 998, + "Α": 999, + "Ε": 1000, + "Η": 1001, + "Ι": 1002, + "Ο": 1003, + "Υ": 1004, + "Ω": 1005, + "ι": 1006, + "Β": 1007, + "Γ": 1008, + "Δ": 1009, + "Ζ": 1010, + "Θ": 1011, + "Κ": 1012, + "Λ": 1013, + "Μ": 1014, + "Ν": 1015, + "Ξ": 1016, + "Π": 1017, + "Ρ": 1018, + "Σ": 1019, + "Τ": 1020, + "Φ": 1021, + "Χ": 1022, + "Ψ": 1023, + "α": 1024, + "ε": 1025, + "η": 1026, + "υ": 1027, + "β": 1028, + "γ": 1029, + "δ": 1030, + "ζ": 1031, + "κ": 1032, + "λ": 1033, + "ν": 1034, + "ξ": 1035, + "ο": 1036, + "π": 1037, + "ρ": 1038, + "ς": 1039, + "σ": 1040, + "τ": 1041, + "φ": 1042, + "χ": 1043, + "ψ": 1044, + "ω": 1045, + "Ϗ": 1046, + "ϗ": 1047, + "Ϙ": 1048, + "ϙ": 1049, + "Ϛ": 1050, + "ϛ": 1051, + "Ϝ": 1052, + "ϝ": 1053, + "Ϟ": 1054, + "ϟ": 1055, + "Ϡ": 1056, + "ϡ": 1057, + "Ϣ": 1058, + "ϣ": 1059, + "Ϥ": 1060, + "ϥ": 1061, + "Ϧ": 1062, + "ϧ": 1063, + "Ϩ": 1064, + "ϩ": 1065, + "Ϫ": 1066, + "ϫ": 1067, + "Ϭ": 1068, + "ϭ": 1069, + "Ϯ": 1070, + "ϯ": 1071, + "ϳ": 1072, + "϶": 1073, + "Ϸ": 1074, + "ϸ": 1075, + "Ϻ": 1076, + "ϻ": 1077, + "ϼ": 1078, + "Ͻ": 1079, + "Ͼ": 1080, + "Ͽ": 1081, + "Е": 1082, + "Ђ": 1083, + "Г": 1084, + "Є": 1085, + "Ѕ": 1086, + "І": 1087, + "Ј": 1088, + "Љ": 1089, + "Њ": 1090, + "Ћ": 1091, + "К": 1092, + "И": 1093, + "У": 1094, + "Џ": 1095, + "А": 1096, + "Б": 1097, + "В": 1098, + "Д": 1099, + "Ж": 1100, + "З": 1101, + "Л": 1102, + "М": 1103, + "Н": 1104, + "О": 1105, + "П": 1106, + "Р": 1107, + "С": 1108, + "Т": 1109, + "Ф": 1110, + "Х": 1111, + "Ц": 1112, + "Ч": 1113, + "Ш": 1114, + "Щ": 1115, + "Ъ": 1116, + "Ы": 1117, + "Ь": 1118, + "Э": 1119, + "Ю": 1120, + "Я": 1121, + "а": 1122, + "б": 1123, + "в": 1124, + "г": 1125, + "д": 1126, + "е": 1127, + "ж": 1128, + "з": 1129, + "и": 1130, + "к": 1131, + "л": 1132, + "м": 1133, + "н": 1134, + "о": 1135, + "п": 1136, + "р": 1137, + "с": 1138, + "т": 1139, + "у": 1140, + "ф": 1141, + "х": 1142, + "ц": 1143, + "ч": 1144, + "ш": 1145, + "щ": 1146, + "ъ": 1147, + "ы": 1148, + "ь": 1149, + "э": 1150, + "ю": 1151, + "я": 1152, + "ђ": 1153, + "є": 1154, + "ѕ": 1155, + "і": 1156, + "ј": 1157, + "љ": 1158, + "њ": 1159, + "ћ": 1160, + "џ": 1161, + "Ѡ": 1162, + "ѡ": 1163, + "Ѣ": 1164, + "ѣ": 1165, + "Ѥ": 1166, + "ѥ": 1167, + "Ѧ": 1168, + "ѧ": 1169, + "Ѩ": 1170, + "ѩ": 1171, + "Ѫ": 1172, + "ѫ": 1173, + "Ѭ": 1174, + "ѭ": 1175, + "Ѯ": 1176, + "ѯ": 1177, + "Ѱ": 1178, + "ѱ": 1179, + "Ѳ": 1180, + "ѳ": 1181, + "Ѵ": 1182, + "ѵ": 1183, + "Ѹ": 1184, + "ѹ": 1185, + "Ѻ": 1186, + "ѻ": 1187, + "Ѽ": 1188, + "ѽ": 1189, + "Ѿ": 1190, + "ѿ": 1191, + "Ҁ": 1192, + "ҁ": 1193, + "҂": 1194, + "҃": 1195, + "҄": 1196, + "҅": 1197, + "҆": 1198, + "҇": 1199, + "҈": 1200, + "҉": 1201, + "Ҋ": 1202, + "ҋ": 1203, + "Ҍ": 1204, + "ҍ": 1205, + "Ҏ": 1206, + "ҏ": 1207, + "Ґ": 1208, + "ґ": 1209, + "Ғ": 1210, + "ғ": 1211, + "Ҕ": 1212, + "ҕ": 1213, + "Җ": 1214, + "җ": 1215, + "Ҙ": 1216, + "ҙ": 1217, + "Қ": 1218, + "қ": 1219, + "Ҝ": 1220, + "ҝ": 1221, + "Ҟ": 1222, + "ҟ": 1223, + "Ҡ": 1224, + "ҡ": 1225, + "Ң": 1226, + "ң": 1227, + "Ҥ": 1228, + "ҥ": 1229, + "Ҧ": 1230, + "ҧ": 1231, + "Ҩ": 1232, + "ҩ": 1233, + "Ҫ": 1234, + "ҫ": 1235, + "Ҭ": 1236, + "ҭ": 1237, + "Ү": 1238, + "ү": 1239, + "Ұ": 1240, + "ұ": 1241, + "Ҳ": 1242, + "ҳ": 1243, + "Ҵ": 1244, + "ҵ": 1245, + "Ҷ": 1246, + "ҷ": 1247, + "Ҹ": 1248, + "ҹ": 1249, + "Һ": 1250, + "һ": 1251, + "Ҽ": 1252, + "ҽ": 1253, + "Ҿ": 1254, + "ҿ": 1255, + "Ӏ": 1256, + "Ӄ": 1257, + "ӄ": 1258, + "Ӆ": 1259, + "ӆ": 1260, + "Ӈ": 1261, + "ӈ": 1262, + "Ӊ": 1263, + "ӊ": 1264, + "Ӌ": 1265, + "ӌ": 1266, + "Ӎ": 1267, + "ӎ": 1268, + "ӏ": 1269, + "Ӕ": 1270, + "ӕ": 1271, + "Ә": 1272, + "ә": 1273, + "Ӡ": 1274, + "ӡ": 1275, + "Ө": 1276, + "ө": 1277, + "Ӷ": 1278, + "ӷ": 1279, + "Ӻ": 1280, + "ӻ": 1281, + "Ӽ": 1282, + "ӽ": 1283, + "Ӿ": 1284, + "ӿ": 1285, + "Ԁ": 1286, + "ԁ": 1287, + "Ԃ": 1288, + "ԃ": 1289, + "Ԅ": 1290, + "ԅ": 1291, + "Ԇ": 1292, + "ԇ": 1293, + "Ԉ": 1294, + "ԉ": 1295, + "Ԋ": 1296, + "ԋ": 1297, + "Ԍ": 1298, + "ԍ": 1299, + "Ԏ": 1300, + "ԏ": 1301, + "Ԑ": 1302, + "ԑ": 1303, + "Ԓ": 1304, + "ԓ": 1305, + "Ԕ": 1306, + "ԕ": 1307, + "Ԗ": 1308, + "ԗ": 1309, + "Ԙ": 1310, + "ԙ": 1311, + "Ԛ": 1312, + "ԛ": 1313, + "Ԝ": 1314, + "ԝ": 1315, + "Ԟ": 1316, + "ԟ": 1317, + "Ԡ": 1318, + "ԡ": 1319, + "Ԣ": 1320, + "ԣ": 1321, + "Ԥ": 1322, + "ԥ": 1323, + "Ԧ": 1324, + "ԧ": 1325, + "Ԩ": 1326, + "ԩ": 1327, + "Ԫ": 1328, + "ԫ": 1329, + "Ԭ": 1330, + "ԭ": 1331, + "Ԯ": 1332, + "ԯ": 1333, + "֑": 1334, + "֒": 1335, + "֓": 1336, + "֔": 1337, + "֕": 1338, + "֖": 1339, + "֗": 1340, + "֘": 1341, + "֙": 1342, + "֚": 1343, + "֛": 1344, + "֜": 1345, + "֝": 1346, + "֞": 1347, + "֟": 1348, + "֠": 1349, + "֡": 1350, + "֢": 1351, + "֣": 1352, + "֤": 1353, + "֥": 1354, + "֦": 1355, + "֧": 1356, + "֨": 1357, + "֩": 1358, + "֪": 1359, + "֫": 1360, + "֬": 1361, + "֭": 1362, + "֮": 1363, + "֯": 1364, + "ְ": 1365, + "ֱ": 1366, + "ֲ": 1367, + "ֳ": 1368, + "ִ": 1369, + "ֵ": 1370, + "ֶ": 1371, + "ַ": 1372, + "ָ": 1373, + "ֹ": 1374, + "ֺ": 1375, + "ֻ": 1376, + "ּ": 1377, + "ֽ": 1378, + "־": 1379, + "ֿ": 1380, + "׀": 1381, + "ׁ": 1382, + "ׂ": 1383, + "׃": 1384, + "ׄ": 1385, + "ׅ": 1386, + "׆": 1387, + "ׇ": 1388, + "א": 1389, + "ב": 1390, + "ג": 1391, + "ד": 1392, + "ה": 1393, + "ו": 1394, + "ז": 1395, + "ח": 1396, + "ט": 1397, + "י": 1398, + "ך": 1399, + "כ": 1400, + "ל": 1401, + "ם": 1402, + "מ": 1403, + "ן": 1404, + "נ": 1405, + "ס": 1406, + "ע": 1407, + "ף": 1408, + "פ": 1409, + "ץ": 1410, + "צ": 1411, + "ק": 1412, + "ר": 1413, + "ש": 1414, + "ת": 1415, + "ׯ": 1416, + "װ": 1417, + "ױ": 1418, + "ײ": 1419, + "׳": 1420, + "״": 1421, + "؀": 1422, + "؁": 1423, + "؂": 1424, + "؃": 1425, + "؄": 1426, + "؅": 1427, + "؆": 1428, + "؇": 1429, + "؈": 1430, + "؉": 1431, + "؊": 1432, + "؋": 1433, + "،": 1434, + "؍": 1435, + "؎": 1436, + "؏": 1437, + "ؐ": 1438, + "ؑ": 1439, + "ؒ": 1440, + "ؓ": 1441, + "ؔ": 1442, + "ؕ": 1443, + "ؖ": 1444, + "ؗ": 1445, + "ؘ": 1446, + "ؙ": 1447, + "ؚ": 1448, + "؛": 1449, + "؜": 1450, + "؝": 1451, + "؞": 1452, + "؟": 1453, + "ؠ": 1454, + "ء": 1455, + "ا": 1456, + "ٓ": 1457, + "ٔ": 1458, + "و": 1459, + "ٕ": 1460, + "ي": 1461, + "ب": 1462, + "ة": 1463, + "ت": 1464, + "ث": 1465, + "ج": 1466, + "ح": 1467, + "خ": 1468, + "د": 1469, + "ذ": 1470, + "ر": 1471, + "ز": 1472, + "س": 1473, + "ش": 1474, + "ص": 1475, + "ض": 1476, + "ط": 1477, + "ظ": 1478, + "ع": 1479, + "غ": 1480, + "ػ": 1481, + "ؼ": 1482, + "ؽ": 1483, + "ؾ": 1484, + "ؿ": 1485, + "ـ": 1486, + "ف": 1487, + "ق": 1488, + "ك": 1489, + "ل": 1490, + "م": 1491, + "ن": 1492, + "ه": 1493, + "ى": 1494, + "ً": 1495, + "ٌ": 1496, + "ٍ": 1497, + "َ": 1498, + "ُ": 1499, + "ِ": 1500, + "ّ": 1501, + "ْ": 1502, + "ٖ": 1503, + "ٗ": 1504, + "٘": 1505, + "ٙ": 1506, + "ٚ": 1507, + "ٛ": 1508, + "ٜ": 1509, + "ٝ": 1510, + "ٞ": 1511, + "ٟ": 1512, + "٠": 1513, + "١": 1514, + "٢": 1515, + "٣": 1516, + "٤": 1517, + "٥": 1518, + "٦": 1519, + "٧": 1520, + "٨": 1521, + "٩": 1522, + "٪": 1523, + "٫": 1524, + "٬": 1525, + "٭": 1526, + "ٮ": 1527, + "ٯ": 1528, + "ٰ": 1529, + "ٱ": 1530, + "ٲ": 1531, + "ٳ": 1532, + "ٴ": 1533, + "ۇ": 1534, + "ٹ": 1535, + "ٺ": 1536, + "ٻ": 1537, + "ټ": 1538, + "ٽ": 1539, + "پ": 1540, + "ٿ": 1541, + "ڀ": 1542, + "ځ": 1543, + "ڂ": 1544, + "ڃ": 1545, + "ڄ": 1546, + "څ": 1547, + "چ": 1548, + "ڇ": 1549, + "ڈ": 1550, + "ډ": 1551, + "ڊ": 1552, + "ڋ": 1553, + "ڌ": 1554, + "ڍ": 1555, + "ڎ": 1556, + "ڏ": 1557, + "ڐ": 1558, + "ڑ": 1559, + "ڒ": 1560, + "ړ": 1561, + "ڔ": 1562, + "ڕ": 1563, + "ږ": 1564, + "ڗ": 1565, + "ژ": 1566, + "ڙ": 1567, + "ښ": 1568, + "ڛ": 1569, + "ڜ": 1570, + "ڝ": 1571, + "ڞ": 1572, + "ڟ": 1573, + "ڠ": 1574, + "ڡ": 1575, + "ڢ": 1576, + "ڣ": 1577, + "ڤ": 1578, + "ڥ": 1579, + "ڦ": 1580, + "ڧ": 1581, + "ڨ": 1582, + "ک": 1583, + "ڪ": 1584, + "ګ": 1585, + "ڬ": 1586, + "ڭ": 1587, + "ڮ": 1588, + "گ": 1589, + "ڰ": 1590, + "ڱ": 1591, + "ڲ": 1592, + "ڳ": 1593, + "ڴ": 1594, + "ڵ": 1595, + "ڶ": 1596, + "ڷ": 1597, + "ڸ": 1598, + "ڹ": 1599, + "ں": 1600, + "ڻ": 1601, + "ڼ": 1602, + "ڽ": 1603, + "ھ": 1604, + "ڿ": 1605, + "ە": 1606, + "ہ": 1607, + "ۃ": 1608, + "ۄ": 1609, + "ۅ": 1610, + "ۆ": 1611, + "ۈ": 1612, + "ۉ": 1613, + "ۊ": 1614, + "ۋ": 1615, + "ی": 1616, + "ۍ": 1617, + "ێ": 1618, + "ۏ": 1619, + "ې": 1620, + "ۑ": 1621, + "ے": 1622, + "۔": 1623, + "ۖ": 1624, + "ۗ": 1625, + "ۘ": 1626, + "ۙ": 1627, + "ۚ": 1628, + "ۛ": 1629, + "ۜ": 1630, + "۝": 1631, + "۞": 1632, + "۟": 1633, + "۠": 1634, + "ۡ": 1635, + "ۢ": 1636, + "ۣ": 1637, + "ۤ": 1638, + "ۥ": 1639, + "ۦ": 1640, + "ۧ": 1641, + "ۨ": 1642, + "۩": 1643, + "۪": 1644, + "۫": 1645, + "۬": 1646, + "ۭ": 1647, + "ۮ": 1648, + "ۯ": 1649, + "۰": 1650, + "۱": 1651, + "۲": 1652, + "۳": 1653, + "۴": 1654, + "۵": 1655, + "۶": 1656, + "۷": 1657, + "۸": 1658, + "۹": 1659, + "ۺ": 1660, + "ۻ": 1661, + "ۼ": 1662, + "۽": 1663, + "۾": 1664, + "ۿ": 1665, + "ऀ": 1666, + "ँ": 1667, + "ं": 1668, + "ः": 1669, + "ऄ": 1670, + "अ": 1671, + "आ": 1672, + "इ": 1673, + "ई": 1674, + "उ": 1675, + "ऊ": 1676, + "ऋ": 1677, + "ऌ": 1678, + "ऍ": 1679, + "ऎ": 1680, + "ए": 1681, + "ऐ": 1682, + "ऑ": 1683, + "ऒ": 1684, + "ओ": 1685, + "औ": 1686, + "क": 1687, + "ख": 1688, + "ग": 1689, + "घ": 1690, + "ङ": 1691, + "च": 1692, + "छ": 1693, + "ज": 1694, + "झ": 1695, + "ञ": 1696, + "ट": 1697, + "ठ": 1698, + "ड": 1699, + "ढ": 1700, + "ण": 1701, + "त": 1702, + "थ": 1703, + "द": 1704, + "ध": 1705, + "न": 1706, + "़": 1707, + "प": 1708, + "फ": 1709, + "ब": 1710, + "भ": 1711, + "म": 1712, + "य": 1713, + "र": 1714, + "ल": 1715, + "ळ": 1716, + "व": 1717, + "श": 1718, + "ष": 1719, + "स": 1720, + "ह": 1721, + "ऺ": 1722, + "ऻ": 1723, + "ऽ": 1724, + "ा": 1725, + "ि": 1726, + "ी": 1727, + "ु": 1728, + "ू": 1729, + "ृ": 1730, + "ॄ": 1731, + "ॅ": 1732, + "ॆ": 1733, + "े": 1734, + "ै": 1735, + "ॉ": 1736, + "ॊ": 1737, + "ो": 1738, + "ौ": 1739, + "्": 1740, + "ॎ": 1741, + "ॏ": 1742, + "ॐ": 1743, + "॑": 1744, + "॒": 1745, + "॓": 1746, + "॔": 1747, + "ॕ": 1748, + "ॖ": 1749, + "ॗ": 1750, + "ॠ": 1751, + "ॡ": 1752, + "ॢ": 1753, + "ॣ": 1754, + "।": 1755, + "॥": 1756, + "०": 1757, + "१": 1758, + "२": 1759, + "३": 1760, + "४": 1761, + "५": 1762, + "६": 1763, + "७": 1764, + "८": 1765, + "९": 1766, + "॰": 1767, + "ॱ": 1768, + "ॲ": 1769, + "ॳ": 1770, + "ॴ": 1771, + "ॵ": 1772, + "ॶ": 1773, + "ॷ": 1774, + "ॸ": 1775, + "ॹ": 1776, + "ॺ": 1777, + "ॻ": 1778, + "ॼ": 1779, + "ॽ": 1780, + "ॾ": 1781, + "ॿ": 1782, + "ᄀ": 1783, + "ᄁ": 1784, + "ᄂ": 1785, + "ᄃ": 1786, + "ᄄ": 1787, + "ᄅ": 1788, + "ᄆ": 1789, + "ᄇ": 1790, + "ᄈ": 1791, + "ᄉ": 1792, + "ᄊ": 1793, + "ᄋ": 1794, + "ᄌ": 1795, + "ᄍ": 1796, + "ᄎ": 1797, + "ᄏ": 1798, + "ᄐ": 1799, + "ᄑ": 1800, + "ᄒ": 1801, + "ᄓ": 1802, + "ᄔ": 1803, + "ᄕ": 1804, + "ᄖ": 1805, + "ᄗ": 1806, + "ᄘ": 1807, + "ᄙ": 1808, + "ᄚ": 1809, + "ᄛ": 1810, + "ᄜ": 1811, + "ᄝ": 1812, + "ᄞ": 1813, + "ᄟ": 1814, + "ᄠ": 1815, + "ᄡ": 1816, + "ᄢ": 1817, + "ᄣ": 1818, + "ᄤ": 1819, + "ᄥ": 1820, + "ᄦ": 1821, + "ᄧ": 1822, + "ᄨ": 1823, + "ᄩ": 1824, + "ᄪ": 1825, + "ᄫ": 1826, + "ᄬ": 1827, + "ᄭ": 1828, + "ᄮ": 1829, + "ᄯ": 1830, + "ᄰ": 1831, + "ᄱ": 1832, + "ᄲ": 1833, + "ᄳ": 1834, + "ᄴ": 1835, + "ᄵ": 1836, + "ᄶ": 1837, + "ᄷ": 1838, + "ᄸ": 1839, + "ᄹ": 1840, + "ᄺ": 1841, + "ᄻ": 1842, + "ᄼ": 1843, + "ᄽ": 1844, + "ᄾ": 1845, + "ᄿ": 1846, + "ᅀ": 1847, + "ᅁ": 1848, + "ᅂ": 1849, + "ᅃ": 1850, + "ᅄ": 1851, + "ᅅ": 1852, + "ᅆ": 1853, + "ᅇ": 1854, + "ᅈ": 1855, + "ᅉ": 1856, + "ᅊ": 1857, + "ᅋ": 1858, + "ᅌ": 1859, + "ᅍ": 1860, + "ᅎ": 1861, + "ᅏ": 1862, + "ᅐ": 1863, + "ᅑ": 1864, + "ᅒ": 1865, + "ᅓ": 1866, + "ᅔ": 1867, + "ᅕ": 1868, + "ᅖ": 1869, + "ᅗ": 1870, + "ᅘ": 1871, + "ᅙ": 1872, + "ᅚ": 1873, + "ᅛ": 1874, + "ᅜ": 1875, + "ᅝ": 1876, + "ᅞ": 1877, + "ᅟ": 1878, + "ᅠ": 1879, + "ᅡ": 1880, + "ᅢ": 1881, + "ᅣ": 1882, + "ᅤ": 1883, + "ᅥ": 1884, + "ᅦ": 1885, + "ᅧ": 1886, + "ᅨ": 1887, + "ᅩ": 1888, + "ᅪ": 1889, + "ᅫ": 1890, + "ᅬ": 1891, + "ᅭ": 1892, + "ᅮ": 1893, + "ᅯ": 1894, + "ᅰ": 1895, + "ᅱ": 1896, + "ᅲ": 1897, + "ᅳ": 1898, + "ᅴ": 1899, + "ᅵ": 1900, + "ᅶ": 1901, + "ᅷ": 1902, + "ᅸ": 1903, + "ᅹ": 1904, + "ᅺ": 1905, + "ᅻ": 1906, + "ᅼ": 1907, + "ᅽ": 1908, + "ᅾ": 1909, + "ᅿ": 1910, + "ᆀ": 1911, + "ᆁ": 1912, + "ᆂ": 1913, + "ᆃ": 1914, + "ᆄ": 1915, + "ᆅ": 1916, + "ᆆ": 1917, + "ᆇ": 1918, + "ᆈ": 1919, + "ᆉ": 1920, + "ᆊ": 1921, + "ᆋ": 1922, + "ᆌ": 1923, + "ᆍ": 1924, + "ᆎ": 1925, + "ᆏ": 1926, + "ᆐ": 1927, + "ᆑ": 1928, + "ᆒ": 1929, + "ᆓ": 1930, + "ᆔ": 1931, + "ᆕ": 1932, + "ᆖ": 1933, + "ᆗ": 1934, + "ᆘ": 1935, + "ᆙ": 1936, + "ᆚ": 1937, + "ᆛ": 1938, + "ᆜ": 1939, + "ᆝ": 1940, + "ᆞ": 1941, + "ᆟ": 1942, + "ᆠ": 1943, + "ᆡ": 1944, + "ᆢ": 1945, + "ᆣ": 1946, + "ᆤ": 1947, + "ᆥ": 1948, + "ᆦ": 1949, + "ᆧ": 1950, + "ᆨ": 1951, + "ᆩ": 1952, + "ᆪ": 1953, + "ᆫ": 1954, + "ᆬ": 1955, + "ᆭ": 1956, + "ᆮ": 1957, + "ᆯ": 1958, + "ᆰ": 1959, + "ᆱ": 1960, + "ᆲ": 1961, + "ᆳ": 1962, + "ᆴ": 1963, + "ᆵ": 1964, + "ᆶ": 1965, + "ᆷ": 1966, + "ᆸ": 1967, + "ᆹ": 1968, + "ᆺ": 1969, + "ᆻ": 1970, + "ᆼ": 1971, + "ᆽ": 1972, + "ᆾ": 1973, + "ᆿ": 1974, + "ᇀ": 1975, + "ᇁ": 1976, + "ᇂ": 1977, + "ᇃ": 1978, + "ᇄ": 1979, + "ᇅ": 1980, + "ᇆ": 1981, + "ᇇ": 1982, + "ᇈ": 1983, + "ᇉ": 1984, + "ᇊ": 1985, + "ᇋ": 1986, + "ᇌ": 1987, + "ᇍ": 1988, + "ᇎ": 1989, + "ᇏ": 1990, + "ᇐ": 1991, + "ᇑ": 1992, + "ᇒ": 1993, + "ᇓ": 1994, + "ᇔ": 1995, + "ᇕ": 1996, + "ᇖ": 1997, + "ᇗ": 1998, + "ᇘ": 1999, + "ᇙ": 2000, + "ᇚ": 2001, + "ᇛ": 2002, + "ᇜ": 2003, + "ᇝ": 2004, + "ᇞ": 2005, + "ᇟ": 2006, + "ᇠ": 2007, + "ᇡ": 2008, + "ᇢ": 2009, + "ᇣ": 2010, + "ᇤ": 2011, + "ᇥ": 2012, + "ᇦ": 2013, + "ᇧ": 2014, + "ᇨ": 2015, + "ᇩ": 2016, + "ᇪ": 2017, + "ᇫ": 2018, + "ᇬ": 2019, + "ᇭ": 2020, + "ᇮ": 2021, + "ᇯ": 2022, + "ᇰ": 2023, + "ᇱ": 2024, + "ᇲ": 2025, + "ᇳ": 2026, + "ᇴ": 2027, + "ᇵ": 2028, + "ᇶ": 2029, + "ᇷ": 2030, + "ᇸ": 2031, + "ᇹ": 2032, + "ᇺ": 2033, + "ᇻ": 2034, + "ᇼ": 2035, + "ᇽ": 2036, + "ᇾ": 2037, + "ᇿ": 2038, + "ẜ": 2039, + "ẝ": 2040, + "ẞ": 2041, + "ẟ": 2042, + "Ỻ": 2043, + "ỻ": 2044, + "Ỽ": 2045, + "ỽ": 2046, + "Ỿ": 2047, + "ỿ": 2048, + "​": 2049, + "‌": 2050, + "‍": 2051, + "[cj_3]": 2052, + "[cj_4]": 2053, + "†": 2054, + "‡": 2055, + "•": 2056, + "‣": 2057, + "‧": 2058, + "[cj_5]": 2059, + "[cj_6]": 2060, + "[cj_7]": 2061, + "[cj_8]": 2062, + "[cj_9]": 2063, + "[cj_.]": 2064, + "[PLACEHOLDER45]": 2065, + "‰": 2066, + "‱": 2067, + "′": 2068, + "‵": 2069, + "‸": 2070, + "‹": 2071, + "›": 2072, + "※": 2073, + "‽": 2074, + "‿": 2075, + "⁀": 2076, + "⁁": 2077, + "⁂": 2078, + "⁃": 2079, + "⁅": 2080, + "⁆": 2081, + "⁊": 2082, + "⁋": 2083, + "⁌": 2084, + "⁍": 2085, + "⁎": 2086, + "⁏": 2087, + "⁐": 2088, + "⁑": 2089, + "⁒": 2090, + "⁓": 2091, + "⁔": 2092, + "⁕": 2093, + "⁖": 2094, + "⁘": 2095, + "⁙": 2096, + "⁚": 2097, + "⁛": 2098, + "⁜": 2099, + "⁝": 2100, + "⁞": 2101, + "⁠": 2102, + "⁡": 2103, + "⁢": 2104, + "⁣": 2105, + "⁤": 2106, + "[fi]": 2107, + "[ta]": 2108, + "[ms]": 2109, + "[he]": 2110, + "": 2111, + "": 2112, + "": 2113, + "": 2114, + "": 2115, + "": 2116, + "−": 2117, + "、": 2118, + "。": 2119, + "〃": 2120, + "〄": 2121, + "々": 2122, + "〆": 2123, + "〇": 2124, + "〈": 2125, + "〉": 2126, + "《": 2127, + "》": 2128, + "「": 2129, + "」": 2130, + "『": 2131, + "』": 2132, + "【": 2133, + "】": 2134, + "〒": 2135, + "〓": 2136, + "〔": 2137, + "〕": 2138, + "〖": 2139, + "〗": 2140, + "〘": 2141, + "〙": 2142, + "〚": 2143, + "〛": 2144, + "〜": 2145, + "〝": 2146, + "〞": 2147, + "〟": 2148, + "ぁ": 2149, + "あ": 2150, + "ぃ": 2151, + "い": 2152, + "ぅ": 2153, + "う": 2154, + "ぇ": 2155, + "え": 2156, + "ぉ": 2157, + "お": 2158, + "か": 2159, + "゙": 2160, + "き": 2161, + "く": 2162, + "け": 2163, + "こ": 2164, + "さ": 2165, + "し": 2166, + "す": 2167, + "せ": 2168, + "そ": 2169, + "た": 2170, + "ち": 2171, + "っ": 2172, + "つ": 2173, + "て": 2174, + "と": 2175, + "な": 2176, + "に": 2177, + "ぬ": 2178, + "ね": 2179, + "の": 2180, + "は": 2181, + "゚": 2182, + "ひ": 2183, + "ふ": 2184, + "へ": 2185, + "ほ": 2186, + "ま": 2187, + "み": 2188, + "む": 2189, + "め": 2190, + "も": 2191, + "ゃ": 2192, + "や": 2193, + "ゅ": 2194, + "ゆ": 2195, + "ょ": 2196, + "よ": 2197, + "ら": 2198, + "り": 2199, + "る": 2200, + "れ": 2201, + "ろ": 2202, + "ゎ": 2203, + "わ": 2204, + "ゐ": 2205, + "ゑ": 2206, + "を": 2207, + "ん": 2208, + "ゕ": 2209, + "ゖ": 2210, + "ゝ": 2211, + "゠": 2212, + "ァ": 2213, + "ア": 2214, + "ィ": 2215, + "イ": 2216, + "ゥ": 2217, + "ウ": 2218, + "ェ": 2219, + "エ": 2220, + "ォ": 2221, + "オ": 2222, + "カ": 2223, + "キ": 2224, + "ク": 2225, + "ケ": 2226, + "コ": 2227, + "サ": 2228, + "シ": 2229, + "ス": 2230, + "セ": 2231, + "ソ": 2232, + "タ": 2233, + "チ": 2234, + "ッ": 2235, + "ツ": 2236, + "テ": 2237, + "ト": 2238, + "ナ": 2239, + "ニ": 2240, + "ヌ": 2241, + "ネ": 2242, + "ノ": 2243, + "ハ": 2244, + "ヒ": 2245, + "フ": 2246, + "ヘ": 2247, + "ホ": 2248, + "マ": 2249, + "ミ": 2250, + "ム": 2251, + "メ": 2252, + "モ": 2253, + "ャ": 2254, + "ヤ": 2255, + "ュ": 2256, + "ユ": 2257, + "ョ": 2258, + "ヨ": 2259, + "ラ": 2260, + "リ": 2261, + "ル": 2262, + "レ": 2263, + "ロ": 2264, + "ヮ": 2265, + "ワ": 2266, + "ヰ": 2267, + "ヱ": 2268, + "ヲ": 2269, + "ン": 2270, + "ヵ": 2271, + "ヶ": 2272, + "・": 2273, + "ー": 2274, + "ヽ": 2275, + "ㄅ": 2276, + "ㄆ": 2277, + "ㄇ": 2278, + "ㄈ": 2279, + "ㄉ": 2280, + "ㄊ": 2281, + "ㄋ": 2282, + "ㄌ": 2283, + "ㄍ": 2284, + "ㄎ": 2285, + "ㄏ": 2286, + "ㄐ": 2287, + "ㄑ": 2288, + "ㄒ": 2289, + "ㄓ": 2290, + "ㄔ": 2291, + "ㄕ": 2292, + "ㄖ": 2293, + "ㄗ": 2294, + "ㄘ": 2295, + "ㄙ": 2296, + "ㄚ": 2297, + "ㄛ": 2298, + "ㄜ": 2299, + "ㄝ": 2300, + "ㄞ": 2301, + "ㄟ": 2302, + "ㄠ": 2303, + "ㄡ": 2304, + "ㄢ": 2305, + "ㄣ": 2306, + "ㄤ": 2307, + "ㄥ": 2308, + "ㄦ": 2309, + "ㄧ": 2310, + "ㄨ": 2311, + "ㄩ": 2312, + "ㄪ": 2313, + "ㄫ": 2314, + "ㄬ": 2315, + "ㄭ": 2316, + "ㄮ": 2317, + "ㄯ": 2318, + "ph": 2319, + "rr": 2320, + "gn": 2321, + "ng": 2322, + "dt": 2323, + "sj": 2324, + "uw": 2325, + "ff": 2326, + "gg": 2327, + "kk": 2328, + "nn": 2329, + "mm": 2330, + "ss": 2331, + "tt": 2332, + "zz": 2333, + "ds": 2334, + "ai": 2335, + "au": 2336, + "ea": 2337, + "ee": 2338, + "ei": 2339, + "eu": 2340, + "ew": 2341, + "ij": 2342, + "oa": 2343, + "oi": 2344, + "oo": 2345, + "ue": 2346, + "eau": 2347, + "tch": 2348, + "sch": 2349, + "🙊": 2350, + "🤭": 2351, + "€": 2352, + "أ": 2353, + "إ": 2354, + "ئ": 2355, + "آ": 2356, + "ؤ": 2357, + "ﻻ": 2358, + "ﺃ": 2359, + "ę": 2360, + "ą": 2361, + "ż": 2362, + "ś": 2363, + "ć": 2364, + "ń": 2365, + "ź": 2366, + "Ś": 2367, + "Ź": 2368, + "Ż": 2369, + "Ć": 2370, + "Š": 2371, + "Ő": 2372, + "й": 2373, + "ё": 2374, + "Й": 2375, + "Ё": 2376, + "が": 2377, + "で": 2378, + "じ": 2379, + "だ": 2380, + "ど": 2381, + "ば": 2382, + "げ": 2383, + "ご": 2384, + "ぶ": 2385, + "ぎ": 2386, + ",": 2387, + "(": 2388, + ":": 2389, + ";": 2390, + "?": 2391, + "!": 2392, + "#": 2393, + " )": 2394, + "ά": 2395, + "ό": 2396, + "ί": 2397, + "έ": 2398, + "ή": 2399, + "ύ": 2400, + "ώ": 2401, + "Έ": 2402, + "Ό": 2403, + "Ή": 2404, + "ž": 2405, + "š": 2406, + "ū": 2407, + "ş": 2408, + "Ō": 2409, + "ī": 2410, + "č": 2411, + "ř": 2412, + "ă": 2413, + "이": 2414, + "기": 2415, + "요": 2416, + "에": 2417, + "다": 2418, + "을": 2419, + "은": 2420, + "서": 2421, + "니": 2422, + "어": 2423, + "ě": 2424, + "ů": 2425, + "Č": 2426, + "ň": 2427, + "ď": 2428, + "ť": 2429, + "♭": 2430, + "ľ": 2431, + "ĺ": 2432, + "ğ": 2433, + "İ": 2434, + "Ş": 2435, + "ड़": 2436, + "ढ़": 2437, + "ज़": 2438, + "फ़": 2439, + "ख़": 2440, + "क़": 2441, + "ग़": 2442, + "Ά": 2443, + "ϊ": 2444, + "Ί": 2445, + "Ύ": 2446, + "Ώ": 2447, + "ΐ": 2448, + "ϋ": 2449, + "ũ": 2450, + "ụ": 2451, + "ọ": 2452, + "ạ": 2453 + }, + "merges": [ + "t h", + "i n", + "th e", + "a n", + "e r", + "o u", + "r e", + "o n", + "a t", + "e d", + "e n", + "t o", + "in g", + "an d", + "i s", + "a s", + "a l", + "o r", + "o f", + "a r", + "i t", + "e s", + "h e", + "s t", + "l e", + "o m", + "s e", + "b e", + "a d", + "o w", + "l y", + "c h", + "w h", + "th at", + "y ou", + "l i", + "v e", + "a c", + "t i", + "l d", + "m e", + "w as", + "g h", + "i d", + "l l", + "w i", + "en t", + "f or", + "a y", + "r o", + "v er", + "i c", + "h er", + "k e", + "h is", + "n o", + "u t", + "u n", + "i r", + "l o", + "w e", + "r i", + "h a", + "wi th", + "gh t", + "ou t", + "i m", + "i on", + "al l", + "a b", + "on e", + "n e", + "g e", + "ou ld", + "t er", + "m o", + "h ad", + "c e", + "s he", + "g o", + "s h", + "u r", + "a m", + "s o", + "p e", + "m y", + "d e", + "a re", + "b ut", + "om e", + "f r", + "the r", + "f e", + "s u", + "d o", + "c on", + "t e", + "a in", + "er e", + "p o", + "i f", + "the y", + "u s", + "a g", + "t r", + "n ow", + "ou n", + "th is", + "ha ve", + "no t", + "s a", + "i l", + "u p", + "th ing", + "fr om", + "a p", + "h im", + "ac k", + "at ion", + "an t", + "ou r", + "o p", + "li ke", + "u st", + "es s", + "b o", + "o k", + "u l", + "in d", + "e x", + "c om", + "s ome", + "the re", + "er s", + "c o", + "re s", + "m an", + "ar d", + "p l", + "w or", + "w ay", + "ti on", + "f o", + "c a", + "w ere", + "b y", + "at e", + "p ro", + "t ed", + "oun d", + "ow n", + "w ould", + "t s", + "wh at", + "q u", + "al ly", + "i ght", + "c k", + "g r", + "wh en", + "v en", + "c an", + "ou gh", + "in e", + "en d", + "p er", + "ou s", + "o d", + "id e", + "k now", + "t y", + "ver y", + "s i", + "a k", + "wh o", + "ab out", + "i ll", + "the m", + "es t", + "re d", + "y e", + "c ould", + "on g", + "you r", + "the ir", + "e m", + "j ust", + "o ther", + "in to", + "an y", + "wh i", + "u m", + "t w", + "as t", + "d er", + "d id", + "i e", + "be en", + "ac e", + "in k", + "it y", + "b ack", + "t ing", + "b r", + "mo re", + "a ke", + "p p", + "the n", + "s p", + "e l", + "u se", + "b l", + "sa id", + "o ver", + "ge t", + "ɑ ː", + "i ː", + "u ː", + "ɜ ː", + "ɔ ː", + "o ː", + "e ɪ", + "o ʊ", + "a ɪ", + "a ʊ", + "ɔ ɪ", + "d ʒ", + "t ʃ", + "ɪ ŋ", + "ᵻ d", + "ˈ iː", + "ˌ iː", + "ˈ ɪ", + "ˌ ɪ", + "ˈ eɪ", + "ˌ eɪ", + "ˈ ɛ", + "ˌ ɛ", + "ˈ æ", + "ˌ æ", + "ˈ ɑː", + "ˌ ɑː", + "ˈ ɔː", + "ˌ ɔː", + "oː ɹ", + "ˈ oːɹ", + "ˌ oːɹ", + "ˈ oʊ", + "ˌ oʊ", + "ˈ ʊ", + "ˌ ʊ", + "ˈ uː", + "ˌ uː", + "ˈ ɜː", + "ˌ ɜː", + "ˈ ʌ", + "ˌ ʌ", + "ˈ aɪ", + "ˌ aɪ", + "ˈ aʊ", + "ˌ aʊ", + "ˈ ɔɪ", + "ˌ ɔɪ", + "ˈ ɚ", + "ˌ ɐ" + ] + } +} \ No newline at end of file diff --git a/t3_mtl23ls_v2.safetensors b/t3_mtl23ls_v2.safetensors new file mode 100644 index 0000000..482ccdb --- /dev/null +++ b/t3_mtl23ls_v2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1237586127ce98e7800a68e49938eb5092846862aabcb6e17b2fda7889a6c75 +size 2143989752