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

vocab.json

@@ -0,0 +1,59 @@
+{
+  " ": 56,
+  "'": 45,
+  "-": 55,
+  "a": 1,
+  "b": 21,
+  "d": 20,
+  "e": 12,
+  "f": 34,
+  "g": 5,
+  "h": 22,
+  "i": 6,
+  "j": 27,
+  "k": 8,
+  "l": 16,
+  "m": 23,
+  "n": 2,
+  "o": 19,
+  "p": 17,
+  "r": 10,
+  "s": 13,
+  "t": 11,
+  "u": 7,
+  "v": 24,
+  "w": 18,
+  "y": 15,
+  "z": 14,
+  "|": 0,
+  "à": 31,
+  "á": 32,
+  "ã": 25,
+  "è": 36,
+  "é": 38,
+  "ì": 28,
+  "í": 35,
+  "ñ": 40,
+  "ò": 41,
+  "ó": 44,
+  "õ": 46,
+  "ù": 37,
+  "ú": 39,
+  "ĩ": 47,
+  "ń": 43,
+  "ň": 54,
+  "ŏ": 52,
+  "ũ": 33,
+  "ǎ": 42,
+  "ǐ": 50,
+  "ǹ": 48,
+  "ɓ": 9,
+  "ɔ": 3,
+  "ɛ": 4,
+  "̀": 29,
+  "́": 30,
+  "̃": 26,
+  "̆": 53,
+  "̌": 51,
+  "ṹ": 49
+}