Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 60
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "་",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "bod",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "་",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,62 @@
+{
+  " ": 59,
+  "་": 0,
+  "ཀ": 19,
+  "ཁ": 17,
+  "ག": 4,
+  "ང": 7,
+  "ཅ": 22,
+  "ཆ": 25,
+  "ཇ": 41,
+  "ཉ": 31,
+  "ཊ": 57,
+  "ཌ": 56,
+  "ཏ": 30,
+  "ཐ": 27,
+  "ད": 3,
+  "ན": 6,
+  "པ": 16,
+  "ཕ": 23,
+  "བ": 8,
+  "མ": 9,
+  "ཙ": 38,
+  "ཚ": 33,
+  "ཛ": 43,
+  "ཝ": 54,
+  "ཞ": 21,
+  "ཟ": 34,
+  "འ": 14,
+  "ཡ": 18,
+  "ར": 10,
+  "ལ": 15,
+  "ཤ": 28,
+  "ས": 1,
+  "ཧ": 47,
+  "ཨ": 45,
+  "ཪ": 58,
+  "ཱ": 35,
+  "ི": 2,
+  "ུ": 11,
+  "ེ": 12,
+  "ཻ": 55,
+  "ོ": 5,
+  "ྐ": 29,
+  "ྒ": 32,
+  "ྔ": 44,
+  "ྕ": 52,
+  "ྗ": 42,
+  "ྙ": 48,
+  "ྟ": 26,
+  "ྡ": 37,
+  "ྣ": 24,
+  "ྤ": 40,
+  "ྦ": 50,
+  "ྨ": 39,
+  "ྩ": 46,
+  "ྫ": 51,
+  "ྭ": 53,
+  "ྱ": 13,
+  "ྲ": 20,
+  "ླ": 36,
+  "ྷ": 49
+}