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

vocab.json

@@ -0,0 +1,50 @@
+{
+  " ": 47,
+  "'": 31,
+  "-": 38,
+  "0": 35,
+  "1": 37,
+  "2": 39,
+  "3": 42,
+  "4": 40,
+  "5": 41,
+  "6": 43,
+  "7": 44,
+  "8": 46,
+  "9": 45,
+  "a": 2,
+  "b": 16,
+  "c": 28,
+  "d": 18,
+  "e": 22,
+  "g": 4,
+  "h": 3,
+  "i": 10,
+  "j": 21,
+  "k": 9,
+  "l": 14,
+  "m": 5,
+  "n": 1,
+  "o": 23,
+  "p": 15,
+  "r": 6,
+  "s": 24,
+  "t": 11,
+  "u": 7,
+  "v": 33,
+  "y": 13,
+  "|": 0,
+  "â": 8,
+  "ê": 20,
+  "ô": 19,
+  "ă": 12,
+  "đ": 27,
+  "ĕ": 29,
+  "ĭ": 34,
+  "ŏ": 25,
+  "ŭ": 26,
+  "ƀ": 30,
+  "ơ": 17,
+  "ư": 36,
+  "̆": 32
+}