Upload tokenizer

special_tokens_map.json

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

tokenizer_config.json

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

vocab.json

@@ -0,0 +1,74 @@
+{
+  " ": 26,
+  "'": 22,
+  "-": 21,
+  "0": 30,
+  "1": 36,
+  "2": 53,
+  "3": 55,
+  "4": 19,
+  "5": 64,
+  "6": 46,
+  "7": 13,
+  "8": 29,
+  "9": 34,
+  "_": 20,
+  "m": 37,
+  "q": 11,
+  "ก": 68,
+  "ข": 58,
+  "ค": 10,
+  "ง": 38,
+  "จ": 70,
+  "ช": 54,
+  "ซ": 69,
+  "ญ": 56,
+  "ฎ": 33,
+  "ฐ": 60,
+  "ณ": 7,
+  "ด": 28,
+  "ต": 27,
+  "ถ": 71,
+  "ท": 31,
+  "ธ": 67,
+  "น": 18,
+  "บ": 41,
+  "ป": 47,
+  "ผ": 4,
+  "พ": 42,
+  "ฟ": 52,
+  "ภ": 24,
+  "ม": 40,
+  "ย": 48,
+  "ร": 3,
+  "ล": 39,
+  "ว": 63,
+  "ศ": 12,
+  "ษ": 65,
+  "ส": 61,
+  "ห": 25,
+  "ฬ": 51,
+  "อ": 62,
+  "ฮ": 32,
+  "ะ": 57,
+  "ั": 44,
+  "า": 8,
+  "ิ": 15,
+  "ี": 0,
+  "ึ": 1,
+  "ื": 16,
+  "ุ": 45,
+  "ู": 59,
+  "ฺ": 9,
+  "เ": 14,
+  "แ": 49,
+  "โ": 5,
+  "ไ": 43,
+  "็": 17,
+  "่": 2,
+  "้": 6,
+  "๋": 35,
+  "์": 66,
+  "ํ": 23,
+  "‍": 50
+}