{ "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, "z": 4, "oː": 5, "j": 6, "ãː": 7, "ɦ": 8, "ɾ": 9, "d": 10, "i": 11, "ɛ": 12, "p": 13, "ɪ": 14, "k": 15, "ɑ": 16, "l": 17, "ɛː": 18, "n": 19, "s": 20, "v": 21, "ə": 22, "ɛi": 23, "ʋ": 24, "t": 25, "m": 26, "ɣ": 27, "ʏ": 28, "ɔ": 29, "x": 30, "u": 31, "f": 32, "ŋ": 33, "øː": 34, "b": 35, "ɔː": 36, "ʌu": 37, "y": 38, "œy": 39, "tʲ": 40, "w": 41, "ʃ": 42, "t̠ʃ": 43, "ɲ": 44, "ʒ": 45, "iː": 46, "ɡ": 47, "d̠ʒ": 48, "ã": 49 }, "unk_token": "UNK" } }