add tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "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]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,53 @@
+{
+  "[PAD]": 50,
+  "[UNK]": 49,
+  "|": 0,
+  "،": 1,
+  "ء": 2,
+  "آ": 3,
+  "ؤ": 4,
+  "ئ": 5,
+  "ا": 6,
+  "ب": 7,
+  "ت": 8,
+  "ث": 9,
+  "ج": 10,
+  "ح": 11,
+  "خ": 12,
+  "د": 13,
+  "ذ": 14,
+  "ر": 15,
+  "ز": 16,
+  "س": 17,
+  "ش": 18,
+  "ص": 19,
+  "ض": 20,
+  "ط": 21,
+  "ظ": 22,
+  "ع": 23,
+  "غ": 24,
+  "ف": 25,
+  "ق": 26,
+  "ل": 27,
+  "م": 28,
+  "ن": 29,
+  "و": 30,
+  "ى": 31,
+  "ي": 32,
+  "ّ": 33,
+  "ٹ": 34,
+  "پ": 35,
+  "چ": 36,
+  "ڈ": 37,
+  "ڑ": 38,
+  "ژ": 39,
+  "ک": 40,
+  "گ": 41,
+  "ں": 42,
+  "ھ": 43,
+  "ہ": 44,
+  "ۂ": 45,
+  "ی": 46,
+  "ے": 47,
+  "۔": 48
+}