Upload tokenizer

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "<unk>": 31
+  "<unk>": 41
 }

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "pad_token": {
-    "content": "a",
+    "content": "0",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2,14 +2,14 @@
   "add_blank": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "a",
+      "content": "0",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "31": {
+    "41": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -21,10 +21,10 @@
   "clean_up_tokenization_spaces": true,
   "extra_special_tokens": {},
   "is_uroman": false,
-  "language": "bcl",
+  "language": "ceb",
   "model_max_length": 1000000000000000019884624838656,
   "normalize": true,
-  "pad_token": "a",
+  "pad_token": "0",
   "phonemize": false,
   "tokenizer_class": "VitsTokenizer",
   "unk_token": "<unk>",

vocab.json

@@ -1,33 +1,43 @@
 {
-  " ": 30,
-  "'": 27,
-  "-": 21,
-  "a": 0,
-  "b": 14,
-  "c": 22,
-  "d": 9,
-  "e": 18,
-  "f": 23,
-  "g": 4,
-  "h": 17,
-  "i": 3,
-  "j": 20,
-  "k": 7,
-  "l": 12,
-  "m": 8,
-  "n": 2,
-  "o": 5,
-  "p": 13,
-  "q": 28,
-  "r": 15,
-  "s": 6,
-  "t": 10,
-  "u": 11,
-  "v": 26,
-  "w": 19,
-  "x": 29,
-  "y": 16,
-  "z": 25,
-  "|": 1,
-  "—": 24
+  " ": 27,
+  "'": 10,
+  "-": 9,
+  "0": 0,
+  "1": 23,
+  "2": 15,
+  "3": 35,
+  "4": 32,
+  "5": 18,
+  "6": 4,
+  "7": 37,
+  "8": 22,
+  "9": 11,
+  "_": 28,
+  "a": 24,
+  "b": 38,
+  "c": 8,
+  "d": 3,
+  "e": 16,
+  "f": 39,
+  "g": 6,
+  "h": 20,
+  "i": 33,
+  "j": 1,
+  "k": 34,
+  "l": 29,
+  "m": 31,
+  "n": 30,
+  "o": 36,
+  "p": 25,
+  "q": 17,
+  "r": 14,
+  "s": 5,
+  "t": 19,
+  "u": 12,
+  "v": 13,
+  "w": 7,
+  "x": 26,
+  "y": 40,
+  "z": 2,
+  "—": 21
 }