{ "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": "Replace", "pattern": { "String": " WORD_BOUNDARY" }, "content": "" }, { "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, "j": 4, "ɛ": 5, "h": 6, "k": 7, "ɑ": 8, "m": 9, "p": 10, "aʊ": 11, "n": 12, "d": 13, "z": 14, "θ": 15, "ɪ": 16, "ŋ": 17, "l": 18, "aɪ": 19, "s": 20, "ɜː": 21, "t": 22, "w": 23, "v": 24, "ð": 25, "æ": 26, "ɔ": 27, "ɹ": 28, "ʌ": 29, "f": 30, "ə": 31, "b": 32, "iː": 33, "eɪ": 34, "oʊ": 35, "d̠ʒ": 36, "i": 37, "uː": 38, "iə": 39, "ʊ": 40, "ɡ": 41, "t̠ʃ": 42, "ɔɪ": 43, "ʃ": 44, "ʒ": 45, "r": 46, "x": 47, "ɬ": 48, "ɑ̃": 49, "nʲ": 50 }, "unk_token": "UNK" } }