{ "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, "aː": 4, "oː": 5, "a": 6, "b": 7, "x": 8, "v": 9, "øː": 10, "n": 11, "ɛː": 12, "f": 13, "l": 14, "iː": 15, "yː": 16, "j": 17, "uː": 18, "h": 19, "ʊ": 20, "m": 21, "ɔ": 22, "ɪ": 23, "eː": 24, "ə": 25, "d̺": 26, "t̺ʰ": 27, "ɛ": 28, "ŋ": 29, "ç": 30, "œ": 31, "kʰ": 32, "ʀ": 33, "ɡ": 34, "pʰ": 35, "ʏ": 36, "s": 37, "z": 38, "ts": 39, "ʃ": 40, "ɐ": 41, "pf": 42, "t̠ʃ": 43, "d̠ʒ": 44 }, "unk_token": "UNK" } }