CHILDES-phoneme-tokenizer / tokenizer_config.json
codebyzeb's picture
Upload tokenizer
7531c0f verified
raw
history blame contribute delete
807 Bytes
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "UNK",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "PAD",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "UTT_BOUNDARY",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "UTT_BOUNDARY",
"clean_up_tokenization_spaces": true,
"eos_token": "UTT_BOUNDARY",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "PAD",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "UNK"
}