PhoWhishper-medium-callcenter / tokenizer_config.json
datdq's picture
Training in progress, step 25
c1bfb0c
raw
history blame contribute delete
No virus
980 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": 1024,
"pad_token": null,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"special_tokens_map_file": "/home/datdq1/.cache/huggingface/hub/models--vinai--PhoWhisper-small/snapshots/d44d00752724b8b28c5b66517b4720b73062a26c/special_tokens_map.json",
"tokenizer_class": "WhisperTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}