Upload tokenizer

added_tokens.json

@@ -1,5 +1,3 @@
 {
-  "ড়": 84,
-  "ঢ়": 85,
-  "য়": 86
+  "<unk>": 74
 }

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
-  "add_blank": false,
+  "add_blank": true,
   "added_tokens_decoder": {
     "0": {
       "content": "6",
@@ -16,39 +16,17 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "84": {
-      "content": "ড়",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "85": {
-      "content": "ঢ়",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "86": {
-      "content": "য়",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "clean_up_tokenization_spaces": true,
+  "extra_special_tokens": {},
   "is_uroman": false,
   "language": "ben",
   "model_max_length": 1000000000000000019884624838656,
-  "normalize": false,
+  "normalize": true,
   "pad_token": "6",
   "phonemize": false,
   "tokenizer_class": "VitsTokenizer",
-  "unk_token": "<unk>"
+  "unk_token": "<unk>",
+  "verbose": false
 }

vocab.json

@@ -72,15 +72,5 @@
   "ৌ": 44,
   "্": 36,
   "ৎ": 52,
-  "০": 74,
-  "১": 75,
-  "২": 76,
-  "৩": 77,
-  "৪": 78,
-  "৫": 79,
-  "৬": 80,
-  "৭": 81,
-  "৮": 82,
-  "৯": 83,
   "—": 32
 }