Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 74
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "6",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "6",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "ben",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "6",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,76 @@
+{
+  " ": 57,
+  "'": 30,
+  "-": 67,
+  "0": 61,
+  "1": 15,
+  "2": 31,
+  "3": 62,
+  "4": 45,
+  "5": 3,
+  "6": 0,
+  "7": 53,
+  "8": 8,
+  "9": 11,
+  "_": 19,
+  "ঁ": 26,
+  "ং": 25,
+  "ঃ": 13,
+  "অ": 50,
+  "আ": 27,
+  "ই": 24,
+  "ঈ": 33,
+  "উ": 66,
+  "ঊ": 34,
+  "ঋ": 63,
+  "এ": 1,
+  "ঐ": 35,
+  "ও": 54,
+  "ঔ": 49,
+  "ক": 9,
+  "খ": 39,
+  "গ": 71,
+  "ঘ": 7,
+  "ঙ": 70,
+  "চ": 65,
+  "ছ": 23,
+  "জ": 47,
+  "ঝ": 43,
+  "ঞ": 5,
+  "ট": 55,
+  "ঠ": 73,
+  "ড": 21,
+  "ঢ": 22,
+  "ণ": 51,
+  "ত": 42,
+  "থ": 14,
+  "দ": 17,
+  "ধ": 58,
+  "ন": 60,
+  "প": 6,
+  "ফ": 64,
+  "ব": 28,
+  "ভ": 16,
+  "ম": 41,
+  "য": 38,
+  "র": 69,
+  "ল": 10,
+  "শ": 48,
+  "ষ": 46,
+  "স": 20,
+  "হ": 29,
+  "়": 68,
+  "া": 59,
+  "ি": 12,
+  "ী": 18,
+  "ু": 4,
+  "ূ": 40,
+  "ৃ": 2,
+  "ে": 37,
+  "ৈ": 56,
+  "ো": 72,
+  "ৌ": 44,
+  "্": 36,
+  "ৎ": 52,
+  "—": 32
+}