{ "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, "m": 4, "ä": 5, "n̪": 6, "d̠ʒ": 7, "i": 8, "v": 9, "e̞": 10, "h": 11, "u": 12, "ʒ": 13, "d̪": 14, "o̞": 15, "l": 16, "ɾ̪": 17, "t̠ʃ": 18, "p": 19, "j": 20, "s̪": 21, "oʊ": 22, "t̪": 23, "aɪ": 24, "k": 25, "w": 26, "ɡ": 27, "b": 28, "t̠ʃʲ": 29, "e̯ä": 30, "ʃ": 31, "ʃʲ": 32, "ə": 33, "o̯ä": 34, "ɨ": 35, "uɪ": 36, "f": 37, "t̪s̪": 38, "z̪": 39, "əɪ": 40, "eɪ": 41, "tsʲ": 42, "zʲ": 43, "iɪ": 44, "aʊ": 45, "tʲ": 46, "nʲ": 47, "eʊ": 48, "iʊ": 49, "ɾʲ": 50, "mʲ": 51, "bʲ": 52, "sʲ": 53, "kʲ": 54, "lʲ": 55, "eo": 56, "d̠ʒʲ": 57, "dʲ": 58, "pʲ": 59, "əʊ": 60, "fʲ": 61, "oɪ": 62 }, "unk_token": "UNK" } }