131 lines
2.6 KiB
JSON
131 lines
2.6 KiB
JSON
|
|
{
|
||
|
|
"additional_special_tokens": [
|
||
|
|
{
|
||
|
|
"content": "<noise>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<unintelligible>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<laugh>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<music>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<cry>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<scream>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<overlap>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<cough>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<invocation>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<echo>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<applause>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<um>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<cs>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<?>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"content": "<pause>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"bos_token": {
|
||
|
|
"content": "<|begin_of_text|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
"eos_token": {
|
||
|
|
"content": "<|eot_id|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
"pad_token": {
|
||
|
|
"content": "<|finetune_right_pad_id|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
}
|
||
|
|
}
|