Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 71
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "า",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "tha",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "า",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,73 @@
+{
+  " ": 70,
+  "'": 59,
+  "-": 66,
+  "0": 60,
+  "1": 63,
+  "2": 65,
+  "4": 64,
+  "ก": 8,
+  "ข": 23,
+  "ค": 19,
+  "ฆ": 56,
+  "ง": 7,
+  "จ": 17,
+  "ฉ": 50,
+  "ช": 35,
+  "ซ": 43,
+  "ฌ": 69,
+  "ญ": 42,
+  "ฎ": 58,
+  "ฏ": 54,
+  "ฐ": 52,
+  "ฑ": 62,
+  "ฒ": 68,
+  "ณ": 46,
+  "ด": 21,
+  "ต": 20,
+  "ถ": 41,
+  "ท": 13,
+  "ธ": 44,
+  "น": 1,
+  "บ": 27,
+  "ป": 28,
+  "ผ": 40,
+  "ฝ": 51,
+  "พ": 14,
+  "ฟ": 48,
+  "ภ": 49,
+  "ม": 12,
+  "ย": 15,
+  "ร": 3,
+  "ฤ": 53,
+  "ล": 16,
+  "ว": 9,
+  "ศ": 45,
+  "ษ": 47,
+  "ส": 26,
+  "ห": 22,
+  "ฬ": 67,
+  "อ": 6,
+  "ฮ": 55,
+  "ะ": 10,
+  "ั": 11,
+  "า": 0,
+  "ิ": 24,
+  "ี": 18,
+  "ึ": 37,
+  "ื": 33,
+  "ุ": 36,
+  "ู": 30,
+  "เ": 4,
+  "แ": 25,
+  "โ": 39,
+  "ใ": 31,
+  "ไ": 29,
+  "็": 32,
+  "่": 2,
+  "้": 5,
+  "๊": 61,
+  "๋": 57,
+  "์": 34,
+  "ํ": 38
+}