Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 60,
-  "<s>": 59
+  "</s>": 57,
+  "<s>": 56
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "57": {
+    "54": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "58": {
+    "55": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "59": {
+    "56": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "60": {
+    "57": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -41,7 +41,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
-  "target_lang": "kab",
+  "target_lang": "ardz",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

vocab.json

@@ -1,4 +1,62 @@
 {
+  "ardz": {
+    "[PAD]": 55,
+    "[UNK]": 54,
+    "e": 1,
+    "h": 2,
+    "i": 3,
+    "k": 4,
+    "n": 5,
+    "o": 6,
+    "s": 7,
+    "u": 8,
+    "|": 0,
+    "ء": 9,
+    "آ": 10,
+    "أ": 11,
+    "ؤ": 12,
+    "إ": 13,
+    "ئ": 14,
+    "ا": 15,
+    "ب": 16,
+    "ة": 17,
+    "ت": 18,
+    "ث": 19,
+    "ج": 20,
+    "ح": 21,
+    "خ": 22,
+    "د": 23,
+    "ذ": 24,
+    "ر": 25,
+    "ز": 26,
+    "س": 27,
+    "ش": 28,
+    "ص": 29,
+    "ض": 30,
+    "ط": 31,
+    "ظ": 32,
+    "ع": 33,
+    "غ": 34,
+    "ـ": 35,
+    "ف": 36,
+    "ق": 37,
+    "ك": 38,
+    "ل": 39,
+    "م": 40,
+    "ن": 41,
+    "ه": 42,
+    "و": 43,
+    "ى": 44,
+    "ي": 45,
+    "ً": 46,
+    "ٌ": 47,
+    "ٍ": 48,
+    "َ": 49,
+    "ُ": 50,
+    "ِ": 51,
+    "ّ": 52,
+    "ْ": 53
+  },
   "kab": {
     "$": 1,
     "0": 2,