Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 49
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "pad_token": {
+    "content": "|",
+    "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": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "shn",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,51 @@
+{
+  " ": 43,
+  "'": 40,
+  "-": 34,
+  "|": 0,
+  "င": 11,
+  "တ": 9,
+  "ထ": 36,
+  "ပ": 20,
+  "မ": 10,
+  "ယ": 29,
+  "ရ": 39,
+  "လ": 16,
+  "ဝ": 5,
+  "သ": 21,
+  "ဢ": 13,
+  "ိ": 15,
+  "ီ": 31,
+  "ု": 22,
+  "ူ": 12,
+  "ေ": 19,
+  "ဵ": 28,
+  "း": 4,
+  "်": 1,
+  "ျ": 38,
+  "ြ": 35,
+  "ွ": 27,
+  "ၢ": 17,
+  "ၵ": 7,
+  "ၶ": 25,
+  "ၷ": 44,
+  "ၸ": 18,
+  "ၹ": 45,
+  "ၺ": 37,
+  "ၻ": 46,
+  "ၼ": 2,
+  "ၽ": 32,
+  "ၾ": 47,
+  "ၿ": 42,
+  "ႀ": 41,
+  "ႁ": 23,
+  "ႂ": 26,
+  "ႃ": 6,
+  "ႄ": 30,
+  "ႅ": 33,
+  "ႆ": 24,
+  "ႇ": 8,
+  "ႈ": 3,
+  "ႉ": 14,
+  "ႊ": 48
+}