{ "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, "i": 4, "d̪": 5, "ɛ": 6, "b": 7, "aː": 8, "t̠ʃ": 9, "m": 10, "l̪": 11, "s̻": 12, "z̻": 13, "ɡ": 14, "k": 15, "o": 16, "ɑ": 17, "t̪ː": 18, "j": 19, "ø": 20, "n̪": 21, "ɲ": 22, "u": 23, "t̻s̻": 24, "y": 25, "r̪": 26, "h": 27, "oː": 28, "v": 29, "d̠ʒ": 30, "t̪": 31, "eː": 32, "ʃ": 33, "ɟʝ": 34, "s̻ː": 35, "p": 36, "øː": 37, "mː": 38, "z̻ː": 39, "l̪ː": 40, "f": 41, "ɟʝː": 42, "uː": 43, "n̪ː": 44, "iː": 45, "ɲː": 46, "ʃː": 47, "r̪ː": 48, "kː": 49, "ŋ": 50, "t̠ʃː": 51, "jː": 52, "bː": 53, "cç": 54, "t̻s̻ː": 55, "d̪ː": 56, "ɡː": 57, "pː": 58, "ʒ": 59, "vː": 60, "cçː": 61, "fː": 62, "hː": 63, "yː": 64 }, "unk_token": "UNK" } }