{ "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, "ɛ": 4, "kː": 5, "o": 6, "pː": 7, "l": 8, "ɐ": 9, "n": 10, "i": 11, "m": 12, "k": 13, "s": 14, "t": 15, "ɔ": 16, "z": 17, "f": 18, "v": 19, "e": 20, "d": 21, "j": 22, "t̠ʃ": 23, "b": 24, "w": 25, "ɛː": 26, "p": 27, "r": 28, "u": 29, "ɡ": 30, "ʎ": 31, "d̠ʒ": 32, "tː": 33, "ɐː": 34, "ts": 35, "dː": 36, "oː": 37, "iː": 38, "sː": 39, "t̠ʃː": 40, "ɾ": 41, "eː": 42, "dz": 43, "bː": 44, "d̠ʒː": 45, "ɲ": 46, "tsː": 47, "ʃ": 48, "a": 49, "ɔː": 50, "dzː": 51, "ŋ": 52, "h": 53, "uː": 54, "ɡː": 55, "ʒ": 56 }, "unk_token": "UNK" } }