Upload tokenizer

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "gbk",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "ञ",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,68 @@
+{
+  " ": 65,
+  "'": 5,
+  "-": 28,
+  "6": 21,
+  "_": 63,
+  "ँ": 46,
+  "ं": 59,
+  "अ": 23,
+  "आ": 13,
+  "इ": 8,
+  "ई": 64,
+  "उ": 33,
+  "ऊ": 9,
+  "ए": 58,
+  "ऐ": 39,
+  "ऑ": 37,
+  "ओ": 1,
+  "औ": 6,
+  "क": 32,
+  "ख": 54,
+  "ग": 31,
+  "घ": 14,
+  "ङ": 48,
+  "च": 34,
+  "छ": 41,
+  "ज": 57,
+  "झ": 43,
+  "ञ": 0,
+  "ट": 36,
+  "ठ": 61,
+  "ड": 12,
+  "ढ": 26,
+  "ण": 40,
+  "त": 4,
+  "थ": 45,
+  "द": 20,
+  "ध": 47,
+  "न": 22,
+  "प": 15,
+  "फ": 16,
+  "ब": 2,
+  "भ": 38,
+  "म": 60,
+  "य": 24,
+  "र": 10,
+  "ल": 19,
+  "ळ": 11,
+  "व": 30,
+  "श": 53,
+  "ष": 35,
+  "स": 29,
+  "ह": 49,
+  "़": 50,
+  "ा": 56,
+  "ि": 18,
+  "ी": 52,
+  "ु": 62,
+  "ू": 7,
+  "ृ": 55,
+  "े": 3,
+  "ै": 25,
+  "ो": 51,
+  "ौ": 17,
+  "्": 44,
+  "‍": 42,
+  "–": 27
+}