cantomed-base-2 / tokenizer_config.json
thisiskeithkwan's picture
Training in progress, step 2000
87d0552
raw
history blame
804 Bytes
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 448,
"pad_token": null,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"tokenizer_class": "WhisperTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}