Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 36
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "m",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "m",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "extra_special_tokens": {},
+  "is_uroman": false,
+  "language": "crk-script_latin",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "m",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,38 @@
+{
+  " ": 11,
+  "'": 17,
+  "-": 23,
+  "_": 10,
+  "a": 1,
+  "b": 27,
+  "c": 2,
+  "d": 15,
+  "e": 8,
+  "f": 20,
+  "g": 28,
+  "h": 26,
+  "i": 24,
+  "j": 22,
+  "k": 19,
+  "l": 12,
+  "m": 0,
+  "n": 14,
+  "o": 13,
+  "p": 16,
+  "q": 3,
+  "r": 5,
+  "s": 29,
+  "t": 34,
+  "u": 31,
+  "v": 32,
+  "w": 21,
+  "x": 7,
+  "y": 6,
+  "z": 33,
+  "ā": 18,
+  "ē": 9,
+  "ī": 30,
+  "ō": 25,
+  "‐": 35,
+  "—": 4
+}