{ "added_tokens_decoder": { "0": { "content": "|", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "4": { "content": "aʊ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "5": { "content": "aɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "13": { "content": "eɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "26": { "content": "oʊ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "27": { "content": "ɔɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "40": { "content": "[UNK]", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "41": { "content": "[PAD]", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "42": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "43": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "44": { "content": "{'content': '', 'single_word': False, 'lstrip': False, 'rstrip': False, 'normalized': True}", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "45": { "content": "{'content': '', 'single_word': False, 'lstrip': False, 'rstrip': False, 'normalized': True}", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "backend": "custom", "bos_token": "", "do_lower_case": false, "eos_token": "", "extra_special_tokens": [ "{'content': '', 'single_word': False, 'lstrip': False, 'rstrip': False, 'normalized': True}", "{'content': '', 'single_word': False, 'lstrip': False, 'rstrip': False, 'normalized': True}" ], "is_local": false, "local_files_only": false, "model_max_length": 1000000000000000019884624838656, "model_specific_special_tokens": { "word_delimiter_token": "|" }, "pad_token": "[PAD]", "processor_class": "Wav2Vec2Processor", "replace_word_delimiter_char": " ", "target_lang": null, "tokenizer_class": "Wav2Vec2CTCTokenizer", "unk_token": "[UNK]", "word_delimiter_token": "|" }