File size: 1,533 Bytes
cb9ad2c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 | {
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<blank>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "WhitespaceSplit"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"<blank>": 0,
"A": 1,
"E": 2,
"I": 3,
"N": 4,
"O": 5,
"U": 6,
"a": 7,
"b": 8,
"by": 9,
"ch": 10,
"cl": 11,
"d": 12,
"dy": 13,
"e": 14,
"f": 15,
"g": 16,
"gy": 17,
"h": 18,
"hy": 19,
"i": 20,
"j": 21,
"k": 22,
"ky": 23,
"m": 24,
"my": 25,
"n": 26,
"ny": 27,
"o": 28,
"p": 29,
"py": 30,
"r": 31,
"ry": 32,
"s": 33,
"sh": 34,
"t": 35,
"ts": 36,
"ty": 37,
"u": 38,
"v": 39,
"w": 40,
"y": 41,
"z": 42,
"pau": 43
},
"unk_token": "<blank>"
}
} |