144 lines
3.3 KiB
JSON
Executable File
144 lines
3.3 KiB
JSON
Executable File
{
|
||
"version": "1.0",
|
||
"truncation": null,
|
||
"padding": null,
|
||
"normalizer": null,
|
||
"pre_tokenizer": null,
|
||
"post_processor": null,
|
||
"decoder": 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
|
||
}
|
||
],
|
||
"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,
|
||
"d͡": 41,
|
||
"t͡": 42,
|
||
"|": 43,
|
||
"æ": 44,
|
||
"ð": 45,
|
||
"ŋ": 46,
|
||
"ɑ": 47,
|
||
"ɔ": 48,
|
||
"ə": 49,
|
||
"ɚ": 50,
|
||
"ɛ": 51,
|
||
"ɡ": 52,
|
||
"ɪ": 53,
|
||
"ɹ": 54,
|
||
"ʃ": 55,
|
||
"ʊ": 56,
|
||
"ʌ": 57,
|
||
"ʒ": 58,
|
||
"θ": 59,
|
||
"ɐ": 60,
|
||
"ɜ": 61,
|
||
"ᵻ": 62,
|
||
"ɾ": 63,
|
||
"n\u0329": 64,
|
||
"ː": 65,
|
||
"ˈ": 66,
|
||
"ˌ": 67,
|
||
"ʔ": 68,
|
||
"d͡ʒ": 69,
|
||
"aɪ": 70,
|
||
"aʊ": 71,
|
||
"eɪ": 72,
|
||
"oʊ": 73,
|
||
"t͡ʃ": 74,
|
||
"ɔɪ": 75,
|
||
"ɔː": 76,
|
||
"uː": 77,
|
||
"iː": 78,
|
||
"ɑː": 79,
|
||
"oː": 80,
|
||
"ɜː": 81
|
||
},
|
||
"merges": [
|
||
"a ɪ",
|
||
"e ɪ",
|
||
"ɔ ɪ",
|
||
"a ʊ",
|
||
"o ʊ",
|
||
"d͡ ʒ",
|
||
"t͡ ʃ",
|
||
"i ː",
|
||
"o ː",
|
||
"u ː",
|
||
"ɑ ː",
|
||
"ɔ ː",
|
||
"ɜ ː"
|
||
]
|
||
}
|
||
} |