Upload tokenizer

added_tokens.json

@@ -1,5 +1,7 @@
 {
+  "[CLS]": 52,
   "[MASK]": 50,
   "[PAD]": 49,
+  "[SEP]": 51,
   "[UNK]": 48
 }

special_tokens_map.json

@@ -1,4 +1,5 @@
 {
+  "cls_token": "[CLS]",
   "mask_token": {
     "content": "[MASK]",
     "lstrip": false,
@@ -13,6 +14,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "sep_token": "[SEP]",
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,

tokenizer.json

@@ -29,6 +29,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 51,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 52,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -23,15 +23,34 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "51": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
   "do_lower_case": false,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 207,
   "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "strip_accents": null,
-  "tokenizer_class": "G2PTTokenizer",
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }