Quechua_Project_Whisper / tokenizer_config.json
cportoca's picture
Upload processor
11d09bd verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<UNK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<PAD>",
"processor_class": "WhisperProcessor",
"tokenizer_class": "WhisperTokenizer",
"unk_token": "<UNK>"
}