{ "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, "ɔ": 4, "l̪ˠ": 5, "a": 6, "p": 7, "ɐ": 8, "i": 9, "n̪": 10, "e": 11, "ʃ": 12, "f": 13, "ɾ": 14, "ɐ̃": 15, "d̪": 16, "m": 17, "ʒ": 18, "b": 19, "ɯ": 20, "ɛ": 21, "ɐ̃i": 22, "ʁ": 23, "t̪": 24, "s": 25, "o": 26, "ɐ̃u̜": 27, "ũ": 28, "ɡ": 29, "u": 30, "k": 31, "z": 32, "au̜": 33, "ai": 34, "eu̜": 35, "ɐi": 36, "ɲ": 37, "ɛu̜": 38, "ĩ": 39, "ũi": 40, "ɔi": 41, "õ": 42, "õi": 43, "ẽ": 44, "v": 45, "oi": 46, "ʎ": 47, "iu̜": 48, "ui": 49, "ɛi": 50, "ts": 51 }, "unk_token": "UNK" } }