Upload tokenizer

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "<unk>": 39
+  "<unk>": 38
 }

special_tokens_map.json

@@ -1,4 +1,4 @@
 {
-  "pad_token": "ا",
+  "pad_token": "k",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -2,14 +2,14 @@
   "add_blank": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "ا",
+      "content": "k",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "39": {
+    "38": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -20,10 +20,10 @@
   },
   "clean_up_tokenization_spaces": true,
   "is_uroman": false,
-  "language": "ara",
-  "model_max_length": 1000000000000000019884624838656,
+  "language": "eng",
+  "model_max_length": 4096,
   "normalize": true,
-  "pad_token": "ا",
+  "pad_token": "k",
   "phonemize": false,
   "tokenizer_class": "VitsTokenizer",
   "unk_token": "<unk>",

vocab.json

@@ -1,41 +1,40 @@
 {
-  " ": 25,
-  "_": 37,
-  "ء": 26,
-  "آ": 27,
-  "أ": 20,
-  "ؤ": 35,
-  "إ": 4,
-  "ئ": 38,
-  "ا": 0,
-  "ب": 28,
-  "ة": 7,
-  "ت": 12,
-  "ث": 19,
-  "ج": 13,
-  "ح": 23,
-  "خ": 11,
-  "د": 16,
-  "ذ": 6,
-  "ر": 9,
-  "ز": 34,
-  "س": 8,
-  "ش": 32,
-  "ص": 18,
-  "ض": 22,
-  "ط": 10,
-  "ظ": 14,
-  "ع": 3,
-  "غ": 5,
-  "ف": 36,
-  "ق": 33,
-  "ك": 2,
-  "ل": 31,
-  "م": 30,
-  "ن": 1,
-  "ه": 24,
-  "و": 29,
-  "ى": 21,
-  "ي": 15,
-  "–": 17
+  " ": 19,
+  "'": 1,
+  "-": 14,
+  "0": 23,
+  "1": 15,
+  "2": 28,
+  "3": 11,
+  "4": 27,
+  "5": 35,
+  "6": 36,
+  "_": 30,
+  "a": 26,
+  "b": 24,
+  "c": 12,
+  "d": 5,
+  "e": 7,
+  "f": 20,
+  "g": 37,
+  "h": 6,
+  "i": 18,
+  "j": 16,
+  "k": 0,
+  "l": 21,
+  "m": 17,
+  "n": 29,
+  "o": 22,
+  "p": 13,
+  "q": 34,
+  "r": 25,
+  "s": 8,
+  "t": 33,
+  "u": 4,
+  "v": 32,
+  "w": 9,
+  "x": 31,
+  "y": 3,
+  "z": 2,
+  "–": 10
 }