{ "added_tokens_decoder": { "0": { "content": "", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "1": { "content": "", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "3": { "content": "aːi", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "4": { "content": "aːu", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "6": { "content": "bʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "8": { "content": "cʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "9": { "content": "d̪", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "10": { "content": "d̪ʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "11": { "content": "eː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "14": { "content": "gj", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "15": { "content": "gʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "18": { "content": "iː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "21": { "content": "kʃ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "22": { "content": "kʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "24": { "content": "l̩", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "25": { "content": "l̩ː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "28": { "content": "oː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "30": { "content": "pʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "34": { "content": "t̪", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "35": { "content": "t̪ɾ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "36": { "content": "t̪ʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "38": { "content": "uː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "43": { "content": "ɑː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "45": { "content": "ɕc", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "47": { "content": "ɖʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "50": { "content": "ɟʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "55": { "content": "ɹ̩", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "56": { "content": "ɹ̩ː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "58": { "content": "ɽʱ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "62": { "content": "ʈʰ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "64": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "65": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "", "clean_up_tokenization_spaces": false, "do_lower_case": false, "eos_token": "", "extra_special_tokens": {}, "model_max_length": 1000000000000000019884624838656, "pad_token": "", "processor_class": "Wav2Vec2Processor", "replace_word_delimiter_char": " ", "target_lang": null, "tokenizer_class": "Wav2Vec2CTCTokenizer", "unk_token": "", "word_delimiter_token": "|" }