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

vocab.json

@@ -0,0 +1,53 @@
+{
+  " ": 50,
+  "-": 18,
+  "0": 49,
+  "1": 48,
+  "2": 46,
+  "a": 3,
+  "b": 6,
+  "c": 27,
+  "d": 12,
+  "e": 5,
+  "f": 24,
+  "g": 31,
+  "i": 1,
+  "j": 29,
+  "k": 4,
+  "l": 16,
+  "m": 10,
+  "n": 2,
+  "o": 20,
+  "p": 14,
+  "r": 32,
+  "s": 19,
+  "t": 8,
+  "u": 7,
+  "w": 38,
+  "y": 13,
+  "|": 0,
+  "à": 23,
+  "á": 15,
+  "è": 40,
+  "é": 36,
+  "ì": 21,
+  "í": 9,
+  "ï": 47,
+  "ò": 37,
+  "ù": 42,
+  "ú": 30,
+  "ā": 26,
+  "ē": 41,
+  "ī": 22,
+  "ĺ": 44,
+  "ń": 28,
+  "ŋ": 17,
+  "ū": 35,
+  "ǹ": 25,
+  "ɔ": 11,
+  "̀": 43,
+  "́": 34,
+  "̃": 39,
+  "̄": 33,
+  "ḿ": 45
+}