speech2phone-ctc / tokenizer_config.json
indiejoseph's picture
Update tokenizer_config.json
68ff6f1 verified
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"83": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"84": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"do_normalize": false,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"return_attention_mask": false,
"tokenizer_class": "Wav2Vec2Tokenizer",
"unk_token": "[UNK]",
"word_delimiter_token": "|"
}