hubert-xlarge-ll60k_arabic / tokenizer_config.json
nrshoudi's picture
Upload tokenizer
955f216
{
"added_tokens_decoder": {
"36": {
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"37": {
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"38": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"39": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"do_phonemize": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"phone_delimiter_token": " ",
"phonemizer_backend": "espeak",
"phonemizer_lang": "en-us",
"tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
"unk_token": "[UNK]",
"word_delimiter_token": null
}