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

vocab.json

@@ -0,0 +1,37 @@
+{
+  " ": 34,
+  "'": 3,
+  "-": 22,
+  "a": 2,
+  "b": 23,
+  "c": 6,
+  "d": 24,
+  "e": 8,
+  "f": 26,
+  "g": 28,
+  "h": 12,
+  "i": 1,
+  "j": 10,
+  "k": 17,
+  "l": 16,
+  "m": 15,
+  "n": 5,
+  "o": 9,
+  "p": 20,
+  "q": 19,
+  "r": 4,
+  "s": 14,
+  "t": 11,
+  "u": 7,
+  "v": 21,
+  "x": 13,
+  "y": 18,
+  "z": 25,
+  "|": 0,
+  "á": 27,
+  "é": 31,
+  "í": 29,
+  "ñ": 33,
+  "ó": 32,
+  "ú": 30
+}