{ "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, "pʰ": 4, "iː": 5, "i": 6, "aː": 7, "r̥": 8, "ɪ": 9, "ɛ": 10, "t̪ʰ": 11, "s̺": 12, "j": 13, "ä": 14, "k": 15, "ʋ": 16, "ɛː": 17, "r": 18, "ei̯": 19, "θ̻": 20, "l": 21, "n̪": 22, "t̪": 23, "ɬ": 24, "uː": 25, "ð̺̞": 26, "ɡ": 27, "c": 28, "h": 29, "ɔ": 30, "n̪̥": 31, "äu̯": 32, "ŋ̥": 33, "ʏ": 34, "m": 35, "f": 36, "ɔː": 37, "x": 38, "cʰ": 39, "ou̯": 40, "p": 41, "ŋ": 42, "øɪ̯": 43, "äi̯": 44, "ɰ": 45, "ʏː": 46, "u": 47, "ɪː": 48, "œ": 49, "ç": 50, "ə": 51, "œː": 52, "ɲ": 53, "m̥": 54, "ɔi̯": 55, "z": 56, "ɲ̥": 57 }, "unk_token": "UNK" } }