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": "urk",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,52 @@
+{
+  " ": 49,
+  "'": 33,
+  "-": 29,
+  "0": 41,
+  "1": 44,
+  "2": 46,
+  "3": 40,
+  "4": 42,
+  "6": 43,
+  "`": 45,
+  "q": 47,
+  "t": 48,
+  "|": 0,
+  "ก": 6,
+  "ค": 32,
+  "ฆ": 24,
+  "ง": 26,
+  "จ": 20,
+  "ช": 39,
+  "ซ": 14,
+  "ฌ": 25,
+  "ญ": 19,
+  "ด": 10,
+  "ต": 12,
+  "ท": 37,
+  "น": 9,
+  "บ": 15,
+  "ป": 22,
+  "พ": 38,
+  "ฟ": 36,
+  "ม": 17,
+  "ย": 23,
+  "ร": 18,
+  "ล": 16,
+  "ว": 27,
+  "อ": 2,
+  "ฮ": 13,
+  "ะ": 4,
+  "ั": 7,
+  "า": 1,
+  "ิ": 28,
+  "ี": 5,
+  "ึ": 35,
+  "ื": 11,
+  "ุ": 34,
+  "ู": 3,
+  "เ": 8,
+  "แ": 30,
+  "โ": 21,
+  "ํ": 31
+}