Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 31,
-  "<s>": 30
+  "</s>": 39,
+  "<s>": 38
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "28": {
+    "36": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "29": {
+    "37": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "30": {
+    "38": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "31": {
+    "39": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

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