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