{ "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, "m": 4, "a": 5, "s̪": 6, "k": 7, "ɛ": 8, "ɾ": 9, "u": 10, "b": 11, "e": 12, "aʊ̯": 13, "ɡ": 14, "ɐ": 15, "oɪ̯": 16, "z": 17, "i": 18, "õ": 19, "t̪": 20, "eʊ̯": 21, "n̪": 22, "v": 23, "d̪": 24, "ɐ̃ʊ̯̃": 25, "eɪ̯": 26, "d̠ʒ": 27, "ẽɪ̯̃": 28, "p": 29, "r": 30, "ɔ": 31, "o": 32, "l": 33, "ɐ̃": 34, "ĩ": 35, "f": 36, "ɲ": 37, "ũ": 38, "uɪ̯": 39, "w": 40, "ʒ": 41, "iʊ̯": 42, "ʃ": 43, "oʊ̯": 44, "aɪ̯": 45, "ɔɪ̯": 46, "ɣ": 47, "ɛɪ̯": 48, "ɛʊ̯": 49, "ɪ̯": 50 }, "unk_token": "UNK" } }