Upload tokenizer

added_tokens.json

@@ -1,6 +1,4 @@
 {
   "</s>": 87,
-  "<s>": 86,
-  "[PAD]": 85,
-  "[UNK]": 84
+  "<s>": 86
 }

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -1,39 +1,4 @@
 {
-  "added_tokens_decoder": {
-    "84": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "85": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "86": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "87": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
@@ -43,7 +8,6 @@
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "tokenizer_file": null,
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"
 }

vocab.json

@@ -1,88 +1,88 @@
 {
-  "'": 10,
+  "'": 70,
   "[PAD]": 85,
   "[UNK]": 84,
-  "`": 22,
-  "|": 1,
-  "،": 55,
-  "ؑ": 57,
-  "ؓ": 72,
-  "ؔ": 71,
-  "؛": 50,
-  "؟": 36,
+  "`": 81,
+  "|": 33,
+  "،": 65,
+  "ؑ": 80,
+  "ؓ": 18,
+  "ؔ": 38,
+  "؛": 68,
+  "؟": 30,
   "ء": 26,
-  "آ": 8,
-  "أ": 4,
-  "ؤ": 45,
-  "ئ": 48,
-  "ا": 39,
-  "ب": 12,
-  "ت": 67,
-  "ث": 83,
-  "ج": 78,
-  "ح": 66,
-  "خ": 74,
-  "د": 65,
-  "ذ": 5,
-  "ر": 82,
-  "ز": 60,
-  "س": 21,
-  "ش": 41,
-  "ص": 42,
-  "ض": 0,
-  "ط": 20,
-  "ظ": 49,
-  "ع": 17,
-  "غ": 81,
-  "ف": 70,
-  "ق": 46,
-  "ك": 6,
-  "ل": 28,
-  "م": 25,
-  "ن": 11,
-  "ه": 34,
-  "و": 61,
-  "ى": 80,
-  "ي": 52,
-  "ً": 19,
-  "َ": 9,
-  "ُ": 15,
-  "ِ": 31,
+  "آ": 21,
+  "أ": 58,
+  "ؤ": 29,
+  "ئ": 74,
+  "ا": 22,
+  "ب": 11,
+  "ت": 3,
+  "ث": 62,
+  "ج": 0,
+  "ح": 10,
+  "خ": 44,
+  "د": 53,
+  "ذ": 42,
+  "ر": 1,
+  "ز": 64,
+  "س": 14,
+  "ش": 7,
+  "ص": 46,
+  "ض": 66,
+  "ط": 51,
+  "ظ": 17,
+  "ع": 13,
+  "غ": 40,
+  "ف": 56,
+  "ق": 71,
+  "ك": 16,
+  "ل": 2,
+  "م": 34,
+  "ن": 24,
+  "ه": 37,
+  "و": 69,
+  "ى": 50,
+  "ي": 67,
+  "ً": 75,
+  "َ": 82,
+  "ُ": 6,
+  "ِ": 36,
   "ّ": 35,
-  "ْ": 27,
-  "ٓ": 2,
-  "ٔ": 23,
-  "ٗ": 47,
-  "ٰ": 16,
-  "ٹ": 38,
-  "پ": 69,
-  "چ": 40,
-  "ڈ": 54,
-  "ڑ": 33,
-  "ژ": 62,
-  "ک": 64,
-  "گ": 73,
-  "ں": 43,
-  "ھ": 75,
-  "ہ": 59,
-  "ۂ": 13,
-  "ۃ": 56,
-  "ی": 3,
-  "ے": 51,
-  "ۓ": 68,
-  "۔": 7,
-  "’": 79,
-  "…": 76,
-  "ﭨ": 53,
-  "ﮭ": 24,
+  "ْ": 39,
+  "ٓ": 20,
+  "ٔ": 78,
+  "ٗ": 4,
+  "ٰ": 43,
+  "ٹ": 41,
+  "پ": 57,
+  "چ": 59,
+  "ڈ": 45,
+  "ڑ": 73,
+  "ژ": 54,
+  "ک": 83,
+  "گ": 9,
+  "ں": 28,
+  "ھ": 47,
+  "ہ": 32,
+  "ۂ": 25,
+  "ۃ": 76,
+  "ی": 79,
+  "ے": 72,
+  "ۓ": 48,
+  "۔": 31,
+  "’": 61,
+  "…": 55,
+  "ﭨ": 60,
+  "ﮭ": 8,
   "ﮯ": 63,
-  "ﯾ": 29,
-  "ﷲ": 14,
-  "ﷺ": 77,
-  "ﺗ": 32,
-  "ﺘ": 30,
-  "ﺩ": 37,
-  "ﺲ": 58,
-  "ﻧ": 44,
-  "ﻮ": 18
+  "ﯾ": 52,
+  "ﷲ": 49,
+  "ﷺ": 15,
+  "ﺗ": 19,
+  "ﺘ": 23,
+  "ﺩ": 5,
+  "ﺲ": 27,
+  "ﻧ": 77,
+  "ﻮ": 12
 }