tokenizer_config.json

{
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_ponet.PoNetTokenizer",
      null
    ]
  },
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "mask_token": "[MASK]",
  "model_input_names": [
    "input_ids",
    "token_type_ids",
    "attention_mask",
    "segment_ids"
  ],
  "model_max_length": 512,
  "never_split": null,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "special_tokens_map_file": null,
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "PoNetTokenizer",
  "unk_token": "[UNK]"
}