Update tokenizer_config.json
Browse files- tokenizer_config.json +4 -22
tokenizer_config.json
CHANGED
|
@@ -1,31 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"add_blank": true,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "u",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"25": {
|
| 13 |
-
"content": "<unk>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
}
|
| 20 |
-
},
|
| 21 |
"clean_up_tokenization_spaces": true,
|
| 22 |
-
"is_uroman":
|
| 23 |
"language": "mon",
|
| 24 |
"model_max_length": 1000000000000000019884624838656,
|
| 25 |
"normalize": true,
|
| 26 |
-
"pad_token": "
|
| 27 |
"phonemize": false,
|
| 28 |
"tokenizer_class": "VitsTokenizer",
|
| 29 |
-
"unk_token": "<unk>"
|
| 30 |
-
"verbose": false
|
| 31 |
}
|
|
|
|
|
|
| 1 |
{
|
| 2 |
"add_blank": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"is_uroman": false,
|
| 5 |
"language": "mon",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"normalize": true,
|
| 8 |
+
"pad_token": "|",
|
| 9 |
"phonemize": false,
|
| 10 |
"tokenizer_class": "VitsTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
|
|
|
| 12 |
}
|
| 13 |
+
|