Upload tokenizer

added_tokens.json

@@ -1,6 +1,6 @@
 {
-  "</s>": 23,
-  "<s>": 22,
-  "[PAD]": 21,
-  "[UNK]": 20
+  "</s>": 34,
+  "<s>": 33,
+  "[PAD]": 32,
+  "[UNK]": 31
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "20": {
+    "31": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "21": {
+    "32": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "22": {
+    "33": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "23": {
+    "34": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,24 +1,35 @@
 {
-  "[PAD]": 21,
-  "[UNK]": 20,
+  "[PAD]": 32,
+  "[UNK]": 31,
   "a": 1,
   "b": 2,
   "c": 3,
   "d": 4,
   "e": 5,
   "f": 6,
-  "h": 7,
-  "i": 8,
-  "l": 9,
-  "m": 10,
-  "n": 11,
-  "o": 12,
-  "p": 13,
-  "q": 14,
-  "r": 15,
-  "s": 16,
-  "t": 17,
-  "u": 18,
-  "v": 19,
-  "|": 0
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0,
+  "á": 27,
+  "ñ": 28,
+  "š": 29,
+  "ə": 30
 }