ResembleAI/chatterbox
1.8k1.6m
1{2 "version": "1.0",3 "truncation": null,4 "padding": null,5 "added_tokens": [6 {7 "id": 0,8 "special": true,9 "content": "[STOP]",10 "single_word": false,11 "lstrip": false,12 "rstrip": false,13 "normalized": false14 },15 {16 "id": 1,17 "special": true,18 "content": "[UNK]",19 "single_word": false,20 "lstrip": false,21 "rstrip": false,22 "normalized": false23 },24 {25 "id": 2,26 "special": true,27 "content": "[SPACE]",28 "single_word": false,29 "lstrip": false,30 "rstrip": false,31 "normalized": false32 },33 {34 "id": 255,35 "special": true,36 "content": "[START]",37 "single_word": false,38 "lstrip": false,39 "rstrip": false,40 "normalized": false41 },42 {43 "id": 604,44 "content": "[UH]",45 "single_word": false,46 "lstrip": false,47 "rstrip": false,48 "normalized": false,49 "special": true50 },51 {52 "id": 605,53 "content": "[UM]",54 "single_word": false,55 "lstrip": false,56 "rstrip": false,57 "normalized": false,58 "special": true59 },60 {61 "id": 606,62 "content": "[giggle]",63 "single_word": false,64 "lstrip": false,65 "rstrip": false,66 "normalized": false,67 "special": true68 },69 {70 "id": 607,71 "content": "[laughter]",72 "single_word": false,73 "lstrip": false,74 "rstrip": false,75 "normalized": false,76 "special": true77 },78 {79 "id": 608,80 "content": "[guffaw]",81 "single_word": false,82 "lstrip": false,83 "rstrip": false,84 "normalized": false,85 "special": true86 },87 {88 "id": 609,89 "content": "[inhale]",90 "single_word": false,91 "lstrip": false,92 "rstrip": false,93 "normalized": false,94 "special": true95 },96 {97 "id": 610,98 "content": "[exhale]",99 "single_word": false,100 "lstrip": false,101 "rstrip": false,102 "normalized": false,103 "special": true104 },105 {106 "id": 611,107 "content": "[sigh]",108 "single_word": false,109 "lstrip": false,110 "rstrip": false,111 "normalized": false,112 "special": true113 },114 {115 "id": 612,116 "content": "[cry]",117 "single_word": false,118 "lstrip": false,119 "rstrip": false,120 "normalized": false,121 "special": true122 },123 {124 "id": 613,125 "content": "[bark]",126 "single_word": false,127 "lstrip": false,128 "rstrip": false,129 "normalized": false,130 "special": true131 },132 {133 "id": 614,134 "content": "[howl]",135 "single_word": false,136 "lstrip": false,137 "rstrip": false,138 "normalized": false,139 "special": true140 },141 {142 "id": 615,143 "content": "[meow]",144 "single_word": false,145 "lstrip": false,146 "rstrip": false,147 "normalized": false,148 "special": true149 },150 {151 "id": 616,152 "content": "[singing]",153 "single_word": false,154 "lstrip": false,155 "rstrip": false,156 "normalized": false,157 "special": true158 },159 {160 "id": 617,161 "content": "[music]",162 "single_word": false,163 "lstrip": false,164 "rstrip": false,165 "normalized": false,166 "special": true167 },168 {169 "id": 618,170 "content": "[whistle]",171 "single_word": false,172 "lstrip": false,173 "rstrip": false,174 "normalized": false,175 "special": true176 },177 {178 "id": 619,179 "content": "[humming]",180 "single_word": false,181 "lstrip": false,182 "rstrip": false,183 "normalized": false,184 "special": true185 },186 {187 "id": 620,188 "content": "[gasp]",189 "single_word": false,190 "lstrip": false,191 "rstrip": false,192 "normalized": false,193 "special": true194 },195 {196 "id": 621,197 "content": "[groan]",198 "single_word": false,199 "lstrip": false,200 "rstrip": false,201 "normalized": false,202 "special": true203 },204 {205 "id": 622,206 "content": "[whisper]",207 "single_word": false,208 "lstrip": false,209 "rstrip": false,210 "normalized": false,211 "special": true212 },213 {214 "id": 623,215 "content": "[mumble]",216 "single_word": false,217 "lstrip": false,218 "rstrip": false,219 "normalized": false,220 "special": true221 },222 {223 "id": 624,224 "content": "[sniff]",225 "single_word": false,226 "lstrip": false,227 "rstrip": false,228 "normalized": false,229 "special": true230 },231 {232 "id": 625,233 "content": "[sneeze]",234 "single_word": false,235 "lstrip": false,236 "rstrip": false,237 "normalized": false,238 "special": true239 },240 {241 "id": 626,242 "content": "[cough]",243 "single_word": false,244 "lstrip": false,245 "rstrip": false,246 "normalized": false,247 "special": true248 },249 {250 "id": 627,251 "content": "[snore]",252 "single_word": false,253 "lstrip": false,254 "rstrip": false,255 "normalized": false,256 "special": true257 },258 {259 "id": 628,260 "content": "[chew]",261 "single_word": false,262 "lstrip": false,263 "rstrip": false,264 "normalized": false,265 "special": true266 },267 {268 "id": 629,269 "content": "[sip]",270 "single_word": false,271 "lstrip": false,272 "rstrip": false,273 "normalized": false,274 "special": true275 },276 {277 "id": 630,278 "content": "[clear_throat]",279 "single_word": false,280 "lstrip": false,281 "rstrip": false,282 "normalized": false,283 "special": true284 },285 {286 "id": 631,287 "content": "[kiss]",288 "single_word": false,289 "lstrip": false,290 "rstrip": false,291 "normalized": false,292 "special": true293 },294 {295 "id": 632,296 "content": "[shhh]",297 "single_word": false,298 "lstrip": false,299 "rstrip": false,300 "normalized": false,301 "special": true302 },303 {304 "id": 633,305 "content": "[gibberish]",306 "single_word": false,307 "lstrip": false,308 "rstrip": false,309 "normalized": false,310 "special": true311 },312 {313 "id": 634,314 "content": "[fr]",315 "single_word": false,316 "lstrip": false,317 "rstrip": false,318 "normalized": false,319 "special": false320 },321 {322 "id": 635,323 "content": "[es]",324 "single_word": false,325 "lstrip": false,326 "rstrip": false,327 "normalized": false,328 "special": false329 },330 {331 "id": 636,332 "content": "[de]",333 "single_word": false,334 "lstrip": false,335 "rstrip": false,336 "normalized": false,337 "special": false338 },339 {340 "id": 637,341 "content": "[it]",342 "single_word": false,343 "lstrip": false,344 "rstrip": false,345 "normalized": false,346 "special": false347 },348 {349 "id": 638,350 "content": "[ipa]",351 "single_word": false,352 "lstrip": false,353 "rstrip": false,354 "normalized": false,355 "special": true356 },357 {358 "id": 639,359 "content": "[end_of_label]",360 "single_word": false,361 "lstrip": false,362 "rstrip": false,363 "normalized": false,364 "special": true365 },366 {367 "id": 695,368 "content": "[PLACEHOLDER55]",369 "single_word": false,370 "lstrip": false,371 "rstrip": false,372 "normalized": false,373 "special": true374 },375 {376 "id": 696,377 "content": "[PLACEHOLDER56]",378 "single_word": false,379 "lstrip": false,380 "rstrip": false,381 "normalized": false,382 "special": true383 },384 {385 "id": 697,386 "content": "[PLACEHOLDER57]",387 "single_word": false,388 "lstrip": false,389 "rstrip": false,390 "normalized": false,391 "special": true392 },393 {394 "id": 698,395 "content": "[PLACEHOLDER58]",396 "single_word": false,397 "lstrip": false,398 "rstrip": false,399 "normalized": false,400 "special": true401 },402 {403 "id": 699,404 "content": "[PLACEHOLDER59]",405 "single_word": false,406 "lstrip": false,407 "rstrip": false,408 "normalized": false,409 "special": true410 },411 {412 "id": 700,413 "content": "[PLACEHOLDER60]",414 "single_word": false,415 "lstrip": false,416 "rstrip": false,417 "normalized": false,418 "special": true419 },420 {421 "id": 701,422 "content": "[PLACEHOLDER61]",423 "single_word": false,424 "lstrip": false,425 "rstrip": false,426 "normalized": false,427 "special": true428 },429 {430 "id": 702,431 "content": "[PLACEHOLDER62]",432 "single_word": false,433 "lstrip": false,434 "rstrip": false,435 "normalized": false,436 "special": true437 },438 {439 "id": 703,440 "content": "[PLACEHOLDER63]",441 "single_word": false,442 "lstrip": false,443 "rstrip": false,444 "normalized": false,445 "special": true446 },447 {448 "id": 704,449 "content": "[MASK]",450 "single_word": false,451 "lstrip": false,452 "rstrip": false,453 "normalized": false,454 "special": true455 },456 {457 "id": 705,458 "content": "[PAD]",459 "single_word": false,460 "lstrip": false,461 "rstrip": false,462 "normalized": false,463 "special": true464 },465 {466 "id": 706,467 "content": "[SEP]",468 "single_word": false,469 "lstrip": false,470 "rstrip": false,471 "normalized": false,472 "special": true473 },474 {475 "id": 707,476 "content": "[CLS]",477 "single_word": false,478 "lstrip": false,479 "rstrip": false,480 "normalized": false,481 "special": true482 },483 {484 "id": 708,485 "content": "[en]",486 "single_word": false,487 "lstrip": false,488 "rstrip": false,489 "normalized": false,490 "special": false491 },492 {493 "id": 709,494 "content": "[nl]",495 "single_word": false,496 "lstrip": false,497 "rstrip": false,498 "normalized": false,499 "special": false500 },501 {502 "id": 710,503 "content": "[pt]",504 "single_word": false,505 "lstrip": false,506 "rstrip": false,507 "normalized": false,508 "special": false509 },510 {511 "id": 711,512 "content": "[el]",513 "single_word": false,514 "lstrip": false,515 "rstrip": false,516 "normalized": false,517 "special": false518 },519 {520 "id": 712,521 "content": "[tr]",522 "single_word": false,523 "lstrip": false,524 "rstrip": false,525 "normalized": false,526 "special": false527 },528 {529 "id": 713,530 "content": "[sv]",531 "single_word": false,532 "lstrip": false,533 "rstrip": false,534 "normalized": false,535 "special": false536 },537 {538 "id": 714,539 "content": "[no]",540 "single_word": false,541 "lstrip": false,542 "rstrip": false,543 "normalized": false,544 "special": false545 },546 {547 "id": 715,548 "content": "[da]",549 "single_word": false,550 "lstrip": false,551 "rstrip": false,552 "normalized": false,553 "special": false554 },555 {556 "id": 716,557 "content": "[ru]",558 "single_word": false,559 "lstrip": false,560 "rstrip": false,561 "normalized": false,562 "special": false563 },564 {565 "id": 717,566 "content": "[pl]",567 "single_word": false,568 "lstrip": false,569 "rstrip": false,570 "normalized": false,571 "special": false572 },573 {574 "id": 718,575 "content": "[sk]",576 "single_word": false,577 "lstrip": false,578 "rstrip": false,579 "normalized": false,580 "special": false581 },582 {583 "id": 719,584 "content": "[cs]",585 "single_word": false,586 "lstrip": false,587 "rstrip": false,588 "normalized": false,589 "special": false590 },591 {592 "id": 720,593 "content": "[hu]",594 "single_word": false,595 "lstrip": false,596 "rstrip": false,597 "normalized": false,598 "special": false599 },600 {601 "id": 721,602 "content": "[ar]",603 "single_word": false,604 "lstrip": false,605 "rstrip": false,606 "normalized": false,607 "special": false608 },609 {610 "id": 722,611 "content": "[hi]",612 "single_word": false,613 "lstrip": false,614 "rstrip": false,615 "normalized": false,616 "special": false617 },618 {619 "id": 723,620 "content": "[ja]",621 "single_word": false,622 "lstrip": false,623 "rstrip": false,624 "normalized": false,625 "special": false626 },627 {628 "id": 724,629 "content": "[ko]",630 "single_word": false,631 "lstrip": false,632 "rstrip": false,633 "normalized": false,634 "special": false635 },636 {637 "id": 725,638 "content": "[zh]",639 "single_word": false,640 "lstrip": false,641 "rstrip": false,642 "normalized": false,643 "special": false644 },645 {646 "id": 726,647 "content": "[ro]",648 "single_word": false,649 "lstrip": false,650 "rstrip": false,651 "normalized": false,652 "special": false653 },654 {655 "id": 727,656 "content": "[bg]",657 "single_word": false,658 "lstrip": false,659 "rstrip": false,660 "normalized": false,661 "special": false662 },663 {664 "id": 729,665 "content": "[ea]",666 "single_word": false,667 "lstrip": false,668 "rstrip": false,669 "normalized": false,670 "special": false671 },672 {673 "id": 730,674 "content": "[sw]",675 "single_word": false,676 "lstrip": false,677 "rstrip": false,678 "normalized": false,679 "special": false680 },681 {682 "id": 732,683 "content": "[vi]",684 "single_word": false,685 "lstrip": false,686 "rstrip": false,687 "normalized": false,688 "special": false689 },690 {691 "id": 733,692 "content": "[cj_a]",693 "single_word": false,694 "lstrip": false,695 "rstrip": false,696 "normalized": false,697 "special": true698 },699 {700 "id": 734,701 "content": "[cj_b]",702 "single_word": false,703 "lstrip": false,704 "rstrip": false,705 "normalized": false,706 "special": true707 },708 {709 "id": 735,710 "content": "[cj_c]",711 "single_word": false,712 "lstrip": false,713 "rstrip": false,714 "normalized": false,715 "special": true716 },717 {718 "id": 736,719 "content": "[cj_d]",720 "single_word": false,721 "lstrip": false,722 "rstrip": false,723 "normalized": false,724 "special": true725 },726 {727 "id": 737,728 "content": "[cj_e]",729 "single_word": false,730 "lstrip": false,731 "rstrip": false,732 "normalized": false,733 "special": true734 },735 {736 "id": 738,737 "content": "[cj_f]",738 "single_word": false,739 "lstrip": false,740 "rstrip": false,741 "normalized": false,742 "special": true743 },744 {745 "id": 739,746 "content": "[cj_g]",747 "single_word": false,748 "lstrip": false,749 "rstrip": false,750 "normalized": false,751 "special": true752 },753 {754 "id": 740,755 "content": "[cj_h]",756 "single_word": false,757 "lstrip": false,758 "rstrip": false,759 "normalized": false,760 "special": true761 },762 {763 "id": 741,764 "content": "[cj_i]",765 "single_word": false,766 "lstrip": false,767 "rstrip": false,768 "normalized": false,769 "special": true770 },771 {772 "id": 742,773 "content": "[cj_j]",774 "single_word": false,775 "lstrip": false,776 "rstrip": false,777 "normalized": false,778 "special": true779 },780 {781 "id": 743,782 "content": "[cj_k]",783 "single_word": false,784 "lstrip": false,785 "rstrip": false,786 "normalized": false,787 "special": true788 },789 {790 "id": 744,791 "content": "[cj_l]",792 "single_word": false,793 "lstrip": false,794 "rstrip": false,795 "normalized": false,796 "special": true797 },798 {799 "id": 745,800 "content": "[cj_m]",801 "single_word": false,802 "lstrip": false,803 "rstrip": false,804 "normalized": false,805 "special": true806 },807 {808 "id": 746,809 "content": "[cj_n]",810 "single_word": false,811 "lstrip": false,812 "rstrip": false,813 "normalized": false,814 "special": true815 },816 {817 "id": 747,818 "content": "[cj_o]",819 "single_word": false,820 "lstrip": false,821 "rstrip": false,822 "normalized": false,823 "special": true824 },825 {826 "id": 748,827 "content": "[cj_p]",828 "single_word": false,829 "lstrip": false,830 "rstrip": false,831 "normalized": false,832 "special": true833 },834 {835 "id": 749,836 "content": "[cj_q]",837 "single_word": false,838 "lstrip": false,839 "rstrip": false,840 "normalized": false,841 "special": true842 },843 {844 "id": 750,845 "content": "[cj_r]",846 "single_word": false,847 "lstrip": false,848 "rstrip": false,849 "normalized": false,850 "special": true851 },852 {853 "id": 751,854 "content": "[cj_s]",855 "single_word": false,856 "lstrip": false,857 "rstrip": false,858 "normalized": false,859 "special": true860 },861 {862 "id": 752,863 "content": "[cj_t]",864 "single_word": false,865 "lstrip": false,866 "rstrip": false,867 "normalized": false,868 "special": true869 },870 {871 "id": 753,872 "content": "[cj_u]",873 "single_word": false,874 "lstrip": false,875 "rstrip": false,876 "normalized": false,877 "special": true878 },879 {880 "id": 754,881 "content": "[cj_v]",882 "single_word": false,883 "lstrip": false,884 "rstrip": false,885 "normalized": false,886 "special": true887 },888 {889 "id": 755,890 "content": "[cj_w]",891 "single_word": false,892 "lstrip": false,893 "rstrip": false,894 "normalized": false,895 "special": true896 },897 {898 "id": 756,899 "content": "[cj_x]",900 "single_word": false,901 "lstrip": false,902 "rstrip": false,903 "normalized": false,904 "special": true905 },906 {907 "id": 757,908 "content": "[cj_y]",909 "single_word": false,910 "lstrip": false,911 "rstrip": false,912 "normalized": false,913 "special": true914 },915 {916 "id": 758,917 "content": "[cj_z]",918 "single_word": false,919 "lstrip": false,920 "rstrip": false,921 "normalized": false,922 "special": true923 },924 {925 "id": 759,926 "content": "[cj_0]",927 "single_word": false,928 "lstrip": false,929 "rstrip": false,930 "normalized": false,931 "special": true932 },933 {934 "id": 760,935 "content": "[cj_1]",936 "single_word": false,937 "lstrip": false,938 "rstrip": false,939 "normalized": false,940 "special": true941 },942 {943 "id": 761,944 "content": "[cj_2]",945 "single_word": false,946 "lstrip": false,947 "rstrip": false,948 "normalized": false,949 "special": true950 },951 {952 "id": 2052,953 "content": "[cj_3]",954 "single_word": false,955 "lstrip": false,956 "rstrip": false,957 "normalized": false,958 "special": true959 },960 {961 "id": 2053,962 "content": "[cj_4]",963 "single_word": false,964 "lstrip": false,965 "rstrip": false,966 "normalized": false,967 "special": true968 },969 {970 "id": 2059,971 "content": "[cj_5]",972 "single_word": false,973 "lstrip": false,974 "rstrip": false,975 "normalized": false,976 "special": true977 },978 {979 "id": 2060,980 "content": "[cj_6]",981 "single_word": false,982 "lstrip": false,983 "rstrip": false,984 "normalized": false,985 "special": true986 },987 {988 "id": 2061,989 "content": "[cj_7]",990 "single_word": false,991 "lstrip": false,992 "rstrip": false,993 "normalized": false,994 "special": true995 },996 {997 "id": 2062,998 "content": "[cj_8]",999 "single_word": false,1000 "lstrip": false,1001 "rstrip": false,1002 "normalized": false,1003 "special": true1004 },1005 {1006 "id": 2063,1007 "content": "[cj_9]",1008 "single_word": false,1009 "lstrip": false,1010 "rstrip": false,1011 "normalized": false,1012 "special": true1013 },1014 {1015 "id": 2064,1016 "content": "[cj_.]",1017 "single_word": false,1018 "lstrip": false,1019 "rstrip": false,1020 "normalized": false,1021 "special": true1022 },1023 {1024 "id": 2065,1025 "content": "[PLACEHOLDER45]",1026 "single_word": false,1027 "lstrip": false,1028 "rstrip": false,1029 "normalized": false,1030 "special": true1031 },1032 {1033 "id": 2107,1034 "content": "[fi]",1035 "single_word": false,1036 "lstrip": false,1037 "rstrip": false,1038 "normalized": false,1039 "special": false1040 },1041 {1042 "id": 2108,1043 "content": "[ta]",1044 "single_word": false,1045 "lstrip": false,1046 "rstrip": false,1047 "normalized": false,1048 "special": false1049 },1050 {1051 "id": 2109,1052 "content": "[ms]",1053 "single_word": false,1054 "lstrip": false,1055 "rstrip": false,1056 "normalized": false,1057 "special": false1058 },1059 {1060 "id": 2110,1061 "content": "[he]",1062 "single_word": false,1063 "lstrip": false,1064 "rstrip": false,1065 "normalized": false,1066 "special": true1067 }1068 ],1069 "normalizer": null,1070 "pre_tokenizer": {1071 "type": "Whitespace"1072 },1073 "post_processor": null,1074 "decoder": null,1075 "model": {1076 "type": "BPE",1077 "dropout": null,1078 "unk_token": "[UNK]",1079 "continuing_subword_prefix": null,1080 "end_of_word_suffix": null,1081 "fuse_unk": false,1082 "vocab": {1083 "[STOP]": 0,1084 "[UNK]": 1,1085 "[SPACE]": 2,1086 "!": 3,1087 "'": 4,1088 "(": 5,1089 ")": 6,1090 ",": 7,1091 "-": 8,1092 ".": 9,1093 "/": 10,1094 ":": 11,1095 ";": 12,1096 "?": 13,1097 "a": 14,1098 "b": 15,1099 "c": 16,1100 "d": 17,1101 "e": 18,1102 "f": 19,1103 "g": 20,1104 "h": 21,1105 "i": 22,1106 "j": 23,1107 "k": 24,1108 "l": 25,1109 "m": 26,1110 "n": 27,1111 "o": 28,1112 "p": 29,1113 "q": 30,1114 "r": 31,1115 "s": 32,1116 "t": 33,1117 "u": 34,1118 "v": 35,1119 "w": 36,1120 "x": 37,1121 "y": 38,1122 "z": 39,1123 "th": 40,1124 "in": 41,1125 "the": 42,1126 "an": 43,1127 "er": 44,1128 "ou": 45,1129 "re": 46,1130 "on": 47,1131 "at": 48,1132 "ed": 49,1133 "en": 50,1134 "to": 51,1135 "ing": 52,1136 "and": 53,1137 "is": 54,1138 "as": 55,1139 "al": 56,1140 "or": 57,1141 "of": 58,1142 "ar": 59,1143 "it": 60,1144 "es": 61,1145 "he": 62,1146 "st": 63,1147 "le": 64,1148 "om": 65,1149 "se": 66,1150 "be": 67,1151 "ad": 68,1152 "ow": 69,1153 "ly": 70,1154 "ch": 71,1155 "wh": 72,1156 "that": 73,1157 "you": 74,1158 "li": 75,1159 "ve": 76,1160 "ac": 77,1161 "ti": 78,1162 "ld": 79,1163 "me": 80,1164 "was": 81,1165 "gh": 82,1166 "id": 83,1167 "ll": 84,1168 "wi": 85,1169 "ent": 86,1170 "for": 87,1171 "ay": 88,1172 "ro": 89,1173 "ver": 90,1174 "ic": 91,1175 "her": 92,1176 "ke": 93,1177 "his": 94,1178 "no": 95,1179 "ut": 96,1180 "un": 97,1181 "ir": 98,1182 "lo": 99,1183 "we": 100,1184 "ri": 101,1185 "ha": 102,1186 "with": 103,1187 "ght": 104,1188 "out": 105,1189 "im": 106,1190 "ion": 107,1191 "all": 108,1192 "ab": 109,1193 "one": 110,1194 "ne": 111,1195 "ge": 112,1196 "ould": 113,1197 "ter": 114,1198 "mo": 115,1199 "had": 116,1200 "ce": 117,