{ "added_tokens_decoder": { "3755": { "content": "[UNK]", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "3756": { "content": "[PAD]", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "3757": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3758": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [], "bos_token": "", "clean_up_tokenization_spaces": true, "do_lower_case": false, "eos_token": "", "model_max_length": 1000000000000000019884624838656, "pad_token": "[PAD]", "replace_word_delimiter_char": " ", "target_lang": "zh-HK", "tokenizer_class": "Wav2Vec2CTCTokenizer", "tokenizer_file": null, "unk_token": "[UNK]", "word_delimiter_token": "|" }