Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 58
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "pad_token": {
+    "content": "3",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "3",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "3",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,60 @@
+{
+  " ": 7,
+  "'": 13,
+  "0": 47,
+  "1": 44,
+  "2": 23,
+  "3": 0,
+  "4": 54,
+  "5": 57,
+  "6": 36,
+  "7": 14,
+  "9": 31,
+  "_": 4,
+  "a": 15,
+  "அ": 1,
+  "ஆ": 45,
+  "இ": 38,
+  "ஈ": 2,
+  "உ": 3,
+  "ஊ": 11,
+  "எ": 37,
+  "ஏ": 16,
+  "ஐ": 52,
+  "ஒ": 27,
+  "ஓ": 49,
+  "க": 6,
+  "ங": 50,
+  "ச": 30,
+  "ஜ": 53,
+  "ஞ": 29,
+  "ட": 22,
+  "ண": 48,
+  "த": 41,
+  "ந": 5,
+  "ன": 35,
+  "ப": 46,
+  "ம": 26,
+  "ய": 39,
+  "ர": 25,
+  "ற": 28,
+  "ல": 21,
+  "ள": 43,
+  "ழ": 24,
+  "வ": 17,
+  "ஷ": 55,
+  "ஸ": 33,
+  "ஹ": 19,
+  "ா": 9,
+  "ி": 32,
+  "ீ": 12,
+  "ு": 51,
+  "ூ": 20,
+  "ெ": 10,
+  "ே": 8,
+  "ை": 34,
+  "ொ": 56,
+  "ோ": 42,
+  "ௌ": 40,
+  "்": 18
+}