Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 68
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "extra_special_tokens": {},
+  "is_uroman": false,
+  "language": "urd-script_devanagari",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,70 @@
+{
+  " ": 67,
+  "'": 55,
+  "-": 41,
+  "0": 54,
+  "1": 57,
+  "2": 56,
+  "3": 63,
+  "4": 58,
+  "5": 59,
+  "6": 66,
+  "7": 64,
+  "8": 65,
+  "9": 61,
+  "|": 0,
+  "ँ": 32,
+  "ं": 16,
+  "ः": 62,
+  "अ": 29,
+  "आ": 30,
+  "इ": 33,
+  "ई": 38,
+  "उ": 27,
+  "ऊ": 52,
+  "ए": 31,
+  "ऐ": 48,
+  "ओ": 49,
+  "औ": 36,
+  "क": 2,
+  "ख": 28,
+  "ग": 24,
+  "घ": 50,
+  "च": 37,
+  "छ": 44,
+  "ज": 18,
+  "झ": 45,
+  "ट": 46,
+  "ठ": 47,
+  "ड": 42,
+  "ढ": 53,
+  "त": 10,
+  "थ": 39,
+  "द": 17,
+  "ध": 51,
+  "न": 6,
+  "प": 22,
+  "फ": 34,
+  "ब": 19,
+  "भ": 40,
+  "म": 8,
+  "य": 21,
+  "र": 4,
+  "ल": 13,
+  "व": 25,
+  "श": 35,
+  "स": 7,
+  "ह": 5,
+  "़": 12,
+  "ा": 1,
+  "ि": 11,
+  "ी": 9,
+  "ु": 20,
+  "ू": 26,
+  "े": 3,
+  "ै": 23,
+  "ो": 15,
+  "ौ": 43,
+  "्": 14,
+  "—": 60
+}