TrOCR-Sinhala / tokenizer_config.json
Ransaka's picture
Upload 4 files
2fd114a
raw
history blame
315 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}