{ "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, "n": 4, "oˤ": 5, "t": 6, "y": 7, "ə": 8, "ð": 9, "ʁ": 10, "ɑˤː": 11, "s": 12, "k": 13, "i": 14, "b": 15, "eˤ": 16, "t̠ʃ": 17, "a": 18, "l": 19, "d": 20, "ɡ": 21, "f": 22, "e": 23, "ɛ": 24, "r": 25, "ɔ": 26, "w": 27, "ɔˤ": 28, "m": 29, "uˤ": 30, "j": 31, "ɑ": 32, "u": 33, "ɒ": 34, "iˤ": 35, "ʋ": 36, "h": 37, "œ": 38, "p": 39, "ɕ": 40, "o": 41, "ŋ": 42, "ɒː": 43, "aˤ": 44, "ɜ": 45, "œː": 46, "eː": 47, "aː": 48, "d̠ʒ": 49, "uː": 50, "ɔː": 51, "oː": 52, "iː": 53, "yː": 54 }, "unk_token": "UNK" } }