Files
phonebabylm-phone-deu-eng-s…/tokenizer.json

174 lines
2.8 KiB
JSON
Raw Normal View History

{
"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": 2,
"content": "UTT_BOUNDARY",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Replace",
"pattern": {
"String": "ː"
},
"content": " ː "
},
{
"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": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"UTT_BOUNDARY": {
"id": "UTT_BOUNDARY",
"ids": [
2
],
"tokens": [
"UTT_BOUNDARY"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"UNK": 0,
"PAD": 1,
"UTT_BOUNDARY": 2,
"d": 3,
"a": 4,
"s": 5,
"WORD_BOUNDARY": 6,
"f": 7,
"ɛ": 8,
"ɐ": 9,
"k": 10,
"ə": 11,
"l": 12,
"v": 13,
"o": 14,
"ː": 15,
"n": 16,
"t": 17,
"ɪ": 18,
"aɪ": 19,
"m": 20,
"z": 21,
"e": 22,
"ɡ": 23,
"h": 24,
"aʊ": 25,
"b": 26,
"u": 27,
"x": 28,
"ʊ": 29,
"i": 30,
"ʃ": 31,
"ʏ": 32,
"ts": 33,
"ɔ": 34,
"p": 35,
"ʀ": 36,
"ŋ": 37,
"œ": 38,
"ç": 39,
"y": 40,
"ø": 41,
"j": 42,
"pf": 43,
"ʊɐ": 44,
"eɪ": 45,
"d̠ʒ": 46,
"ɛɪ": 47,
"w": 48,
"ɒ": 49,
"ã": 50,
"t̠ʃ": 51,
"tɕ": 52,
"ð": 53,
"θ": 54,
"ɹ": 55,
"əʊ": 56,
"ʌ": 57,
"eə": 58,
"ɔɪ": 59,
"l̩": 60,
"ʒ": 61,
"ʊə": 62,
"ɔ̃": 63,
"iə": 64,
"œ̃": 65,
"ʔ": 66,
"æ": 67,
"ɑ": 68,
"ɜ": 69,
"oʊ": 70
},
"unk_token": "UNK"
}
}