wav2vec2-kanji-base-char-0916 / tokenizer_config.json
SiRoZaRuPa's picture
Upload tokenizer
f1e3c4e verified
raw
history blame
1.43 kB
{
"added_tokens_decoder": {
"3876": {
"content": "<unk>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"3877": {
"content": "[PAD]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"3878": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3879": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3880": {
"content": "[雑音]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"3881": {
"content": "[無音]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"use_fast": false,
"word_delimiter_token": "|"
}