codebyzeb's picture
Upload tokenizer
d0f7972 verified
raw
history blame
3.05 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "UNK",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "PAD",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "UTT_BOUNDARY",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Replace",
"pattern": {
"String": " WORD_BOUNDARY"
},
"content": ""
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
}
]
},
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "UTT_BOUNDARY",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "UTT_BOUNDARY",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "UTT_BOUNDARY",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"UTT_BOUNDARY": {
"id": "UTT_BOUNDARY",
"ids": [
3
],
"tokens": [
"UTT_BOUNDARY"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"UNK": 0,
"PAD": 1,
"WORD_BOUNDARY": 2,
"UTT_BOUNDARY": 3,
"d": 4,
"uː": 5,
"j": 6,
"w": 7,
"ɔ": 8,
"n": 9,
"t": 10,
"ə": 11,
"l": 12,
"ʊ": 13,
"k": 14,
"æ": 15,
"ð": 16,
"ʌ": 17,
"ɪ": 18,
"s": 19,
"ɛ": 20,
"z": 21,
"iː": 22,
"ɹ": 23,
"f": 24,
"eɪ": 25,
"ɡ": 26,
"ɑ": 27,
"h": 28,
"p": 29,
"b": 30,
"i": 31,
"t̠ʃ": 32,
"aɪ": 33,
"θ": 34,
"ŋ": 35,
"m": 36,
"ɔɪ": 37,
"oʊ": 38,
"aʊ": 39,
"v": 40,
"ɜː": 41,
"d̠ʒ": 42,
"ʃ": 43,
"iə": 44,
"ʒ": 45,
"ɑ̃": 46,
"r": 47,
"nʲ": 48,
"x": 49,
"ɬ": 50,
"ç": 51,
"e": 52,
"o": 53,
"ɛː": 54,
"ɪː": 55,
"u": 56,
"q": 57,
"tɕ": 58,
"tʰ": 59,
"ɯ": 60,
"r̩": 61,
"əʊ": 62,
"a": 63,
"ɒ": 64,
"eə": 65
},
"unk_token": "UNK"
}
}