{ "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, "h": 5, "m": 6, "ai": 7, "ɛ": 8, "r": 9, "t": 10, "ɑː": 11, "p": 12, "d": 13, "iː": 14, "b": 15, "oː": 16, "f": 17, "eː": 18, "χ": 19, "w": 20, "a": 21, "n": 22, "ø": 23, "j": 24, "au": 25, "ə": 26, "ɔi": 27, "ð": 28, "ɪ": 29, "s": 30, "ɡ": 31, "ʊi": 32, "ʊ": 33, "əi": 34, "θ": 35, "l": 36, "ʌ": 37, "ŋ": 38, "v": 39, "k": 40, "ɬ": 41, "ɪu": 42, "uː": 43, "ʃ": 44, "ɛu": 45, "d̠ʒ": 46, "z": 47 }, "unk_token": "UNK" } }