Upload tokenizer

added_tokens.json

@@ -1,6 +1,4 @@
 {
-  "</s>": 54,
-  "<pad>": 56,
-  "<s>": 53,
-  "<unk>": 55
+  "</s>": 62,
+  "<s>": 61
 }

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -40,7 +40,7 @@
       "single_word": false,
       "special": false
     },
-    "53": {
+    "61": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -48,29 +48,13 @@
       "single_word": false,
       "special": true
     },
-    "54": {
+    "62": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "55": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "56": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<s>",
@@ -78,10 +62,10 @@
   "do_lower_case": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": "[UNK]",
   "word_delimiter_token": "|"
 }

vocab.json

@@ -1,55 +1,63 @@
 {
-  " ": 58,
+  " ": 5,
   "[CLS]": 2,
   "[MASK]": 4,
   "[PAD]": 0,
   "[SEP]": 3,
   "[UNK]": 1,
-  "ء": 43,
-  "آ": 46,
-  "أ": 34,
-  "ؤ": 44,
-  "إ": 45,
-  "ئ": 39,
-  "ا": 59,
-  "ب": 55,
-  "ة": 40,
-  "ت": 7,
-  "ث": 8,
-  "ج": 9,
-  "ح": 10,
-  "خ": 11,
-  "د": 12,
-  "ذ": 13,
-  "ر": 14,
-  "ز": 15,
-  "س": 56,
-  "ش": 17,
-  "ص": 18,
-  "ض": 19,
-  "ط": 20,
-  "ظ": 21,
-  "ع": 22,
-  "غ": 23,
-  "ف": 24,
-  "ق": 25,
-  "ك": 26,
-  "ل": 61,
-  "م": 57,
-  "ن": 29,
-  "ه": 62,
-  "و": 31,
+  "ء": 6,
+  "آ": 7,
+  "أ": 8,
+  "ؤ": 9,
+  "إ": 10,
+  "ئ": 11,
+  "ا": 12,
+  "ب": 13,
+  "ة": 14,
+  "ت": 15,
+  "ث": 16,
+  "ج": 17,
+  "ح": 18,
+  "خ": 19,
+  "د": 20,
+  "ذ": 21,
+  "ر": 22,
+  "ز": 23,
+  "س": 24,
+  "ش": 25,
+  "ص": 26,
+  "ض": 27,
+  "ط": 28,
+  "ظ": 29,
+  "ع": 30,
+  "غ": 31,
+  "ـ": 32,
+  "ف": 33,
+  "ق": 34,
+  "ك": 35,
+  "ل": 36,
+  "م": 37,
+  "ن": 38,
+  "ه": 39,
+  "و": 40,
   "ى": 41,
-  "ي": 32,
-  "َ": 48,
-  "ُ": 49,
-  "ِ": 50,
-  "ّ": 51,
-  "ْ": 54,
-  "ٔ": 47,
-  "۝": 64,
-  "۟": 53,
-  "۩": 63,
-  "﴾": 66,
-  "﴿": 65
+  "ي": 42,
+  "ً": 43,
+  "ٌ": 44,
+  "ٍ": 45,
+  "َ": 46,
+  "ُ": 47,
+  "ِ": 48,
+  "ّ": 49,
+  "ْ": 50,
+  "ٓ": 51,
+  "ٰ": 52,
+  "ۖ": 53,
+  "ۗ": 54,
+  "ۘ": 55,
+  "ۙ": 56,
+  "ۚ": 57,
+  "ۛ": 58,
+  "ۜ": 59,
+  "۩": 60
 }