pazarf / tokenizer_config.json
EzekielMW's picture
Fine-tuned on DhoNam Dholuo train split
0006d80 verified
Raw
History Blame Contribute Delete
561 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": [
"<|luo|>"
],
"is_local": false,
"language": null,
"model_max_length": 1000000000000000019884624838656,
"model_specific_special_tokens": {},
"pad_token": "<|endoftext|>",
"predict_timestamps": false,
"processor_class": "WhisperProcessor",
"task": null,
"tokenizer_class": "WhisperTokenizer",
"unk_token": "<|endoftext|>"
}