{ "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, "ð": 4, "æ": 5, "tʰ": 6, "ɡ": 7, "ʊ": 8, "d": 9, "ɑː": 10, "l": 11, "ɪ": 12, "n": 13, "eɪ": 14, "t̠ʃ": 15, "w": 16, "ɒ": 17, "ʌ": 18, "z": 19, "m": 20, "iː": 21, "aɪ": 22, "h": 23, "e": 24, "kʰ": 25, "s": 26, "ə": 27, "ɔː": 28, "ɹ": 29, "i": 30, "əʊ": 31, "uː": 32, "j": 33, "ɪə": 34, "ɔɪ": 35, "v": 36, "f": 37, "ɜː": 38, "b": 39, "pʰ": 40, "d̠ʒ": 41, "ɐ": 42, "eə": 43, "ʃ": 44, "θ": 45, "ŋ": 46, "aʊ": 47, "ʊə": 48, "n̩": 49, "ʒ": 50 }, "unk_token": "UNK" } }