word-stress-tokenizer / tokenizer_config.json
abletobetable's picture
Upload tokenizer
cdce4ea
raw
history blame
216 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"model_max_length": 24,
"pad_token": "<pad>",
"padding_side": "right",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}