Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 65
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "త",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "tel",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "త",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,67 @@
+{
+  " ": 19,
+  "'": 8,
+  "-": 53,
+  "6": 60,
+  "_": 45,
+  "ం": 61,
+  "ః": 28,
+  "అ": 42,
+  "ఆ": 63,
+  "ఇ": 62,
+  "ఈ": 55,
+  "ఉ": 51,
+  "ఊ": 59,
+  "ఎ": 38,
+  "ఏ": 37,
+  "ఐ": 9,
+  "ఒ": 21,
+  "ఓ": 40,
+  "ఔ": 13,
+  "క": 20,
+  "ఖ": 30,
+  "గ": 10,
+  "ఘ": 7,
+  "చ": 46,
+  "ఛ": 57,
+  "జ": 12,
+  "ఞ": 1,
+  "ట": 56,
+  "ఠ": 29,
+  "డ": 16,
+  "ఢ": 52,
+  "ణ": 33,
+  "త": 0,
+  "థ": 3,
+  "ద": 49,
+  "ధ": 24,
+  "న": 5,
+  "ప": 27,
+  "ఫ": 34,
+  "బ": 54,
+  "భ": 2,
+  "మ": 17,
+  "య": 41,
+  "ర": 4,
+  "ల": 50,
+  "ళ": 58,
+  "వ": 23,
+  "శ": 25,
+  "ష": 31,
+  "స": 18,
+  "హ": 14,
+  "ా": 15,
+  "ి": 35,
+  "ీ": 43,
+  "ు": 47,
+  "ూ": 22,
+  "ృ": 39,
+  "ె": 44,
+  "ే": 11,
+  "ై": 64,
+  "ొ": 36,
+  "ో": 6,
+  "ౌ": 26,
+  "్": 48,
+  "–": 32
+}