Update tokenizer
Browse filesUpdate tokenizer to use `NFC` normalization because transformers.js doesn't support `NFD`
- special_tokens_map.json +1 -0
- tokenizer.json +1 -1
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{}
|
tokenizer.json
CHANGED
|
@@ -41,7 +41,7 @@
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
| 44 |
-
"type": "
|
| 45 |
},
|
| 46 |
"pre_tokenizer": {
|
| 47 |
"type": "Split",
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
| 44 |
+
"type": "NFC"
|
| 45 |
},
|
| 46 |
"pre_tokenizer": {
|
| 47 |
"type": "Split",
|