{ | |
"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": "WORD_BOUNDARY", | |
"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": "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, | |
"n": 4, | |
"o": 5, | |
"t": 6, | |
"ʃ": 7, | |
"a": 8, | |
"uː": 9, | |
"m": 10, | |
"u": 11, | |
"tʲ": 12, | |
"i": 13, | |
"s": 14, | |
"eː": 15, | |
"d": 16, | |
"iː": 17, | |
"k": 18, | |
"ɡ": 19, | |
"ɑ": 20, | |
"ɤ": 21, | |
"ʊ": 22, | |
"sʲ": 23, | |
"j": 24, | |
"aː": 25, | |
"h": 26, | |
"v": 27, | |
"æi": 28, | |
"kː": 29, | |
"e": 30, | |
"ɪ": 31, | |
"tː": 32, | |
"r": 33, | |
"ɛ": 34, | |
"mː": 35, | |
"p": 36, | |
"sː": 37, | |
"æ": 38, | |
"l": 39, | |
"pː": 40, | |
"yː": 41, | |
"æː": 42, | |
"b": 43, | |
"ɔ": 44, | |
"ɤː": 45, | |
"lː": 46, | |
"ø": 47, | |
"øː": 48, | |
"ŋ": 49, | |
"y": 50, | |
"oː": 51, | |
"rː": 52, | |
"ɲ": 53, | |
"nː": 54, | |
"w": 55, | |
"tʲː": 56, | |
"øɪ̯": 57, | |
"f": 58, | |
"dʲ": 59, | |
"sʲː": 60, | |
"t̠ʃ": 61, | |
"ʃː": 62, | |
"ʒ": 63, | |
"z": 64, | |
"fː": 65, | |
"dː": 66, | |
"yi": 67 | |
}, | |
"unk_token": "UNK" | |
} | |
} |