{ "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": "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, "s": 4, "æ": 5, "n": 6, "o": 7, "j": 8, "ʊ": 9, "ɔ": 10, "a": 11, "r": 12, "m": 13, "ɯ": 14, "k": 15, "ɪ": 16, "l": 17, "i": 18, "ɛ": 19, "v": 20, "d": 21, "d̠ʒ": 22, "y": 23, "t": 24, "b": 25, "u": 26, "z": 27, "ʃ": 28, "ɟ": 29, "e": 30, "p": 31, "ɡ": 32, "ɫ": 33, "h": 34, "t̠ʃ": 35, "ɾ": 36, "f": 37, "ø": 38, "œ": 39, "aː": 40, "c": 41, "ʊː": 42, "tː": 43, "oː": 44, "œː": 45, "ʒ": 46 }, "unk_token": "UNK" } }