Upload tokenizer
Browse files- added_tokens.json +3 -0
- tokenizer_config.json +20 -1
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<unk>": 38
|
| 3 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,23 @@
|
|
| 1 |
{
|
| 2 |
"add_blank": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"is_uroman": false,
|
| 5 |
"language": "kmr-script_arabic",
|
|
@@ -8,5 +26,6 @@
|
|
| 8 |
"pad_token": "|",
|
| 9 |
"phonemize": false,
|
| 10 |
"tokenizer_class": "VitsTokenizer",
|
| 11 |
-
"unk_token": "<unk>"
|
|
|
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_blank": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "|",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"38": {
|
| 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": false,
|
| 23 |
"language": "kmr-script_arabic",
|
|
|
|
| 26 |
"pad_token": "|",
|
| 27 |
"phonemize": false,
|
| 28 |
"tokenizer_class": "VitsTokenizer",
|
| 29 |
+
"unk_token": "<unk>",
|
| 30 |
+
"verbose": false
|
| 31 |
}
|