Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 44,
-  "<s>": 43
+  "</s>": 38,
+  "<s>": 37
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "41": {
+    "35": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "42": {
+    "36": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "43": {
+    "37": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "44": {
+    "38": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -6,8 +6,8 @@
   "5": 5,
   "7": 6,
   "9": 7,
-  "[PAD]": 42,
-  "[UNK]": 41,
+  "[PAD]": 36,
+  "[UNK]": 35,
   "a": 8,
   "b": 9,
   "c": 10,
@@ -24,22 +24,16 @@
   "n": 21,
   "o": 22,
   "p": 23,
-  "q": 24,
-  "r": 25,
-  "s": 26,
-  "t": 27,
-  "u": 28,
-  "v": 29,
-  "w": 30,
-  "x": 31,
-  "y": 32,
-  "z": 33,
+  "r": 24,
+  "s": 25,
+  "t": 26,
+  "u": 27,
+  "v": 28,
+  "w": 29,
+  "x": 30,
+  "y": 31,
+  "z": 32,
   "|": 0,
-  "á": 34,
-  "é": 35,
-  "ó": 36,
-  "ŋ": 37,
-  "š": 38,
-  "η": 39,
-  "ղ": 40
+  "ŋ": 33,
+  "η": 34
 }