add tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,54 @@
+{
+  "[PAD]": 51,
+  "[UNK]": 50,
+  "|": 44,
+  "ء": 3,
+  "آ": 5,
+  "أ": 32,
+  "ؤ": 35,
+  "ئ": 38,
+  "ا": 46,
+  "ب": 25,
+  "ت": 19,
+  "ث": 2,
+  "ج": 49,
+  "ح": 39,
+  "خ": 31,
+  "د": 27,
+  "ذ": 10,
+  "ر": 0,
+  "ز": 33,
+  "س": 28,
+  "ش": 42,
+  "ص": 43,
+  "ض": 26,
+  "ط": 45,
+  "ظ": 15,
+  "ع": 4,
+  "غ": 11,
+  "ف": 8,
+  "ق": 7,
+  "ل": 41,
+  "م": 37,
+  "ن": 36,
+  "ه": 21,
+  "و": 48,
+  "ى": 17,
+  "ي": 22,
+  "ٹ": 9,
+  "پ": 30,
+  "چ": 40,
+  "ڈ": 16,
+  "ڑ": 14,
+  "ژ": 47,
+  "ک": 1,
+  "گ": 13,
+  "ں": 23,
+  "ھ": 24,
+  "ہ": 34,
+  "ۂ": 29,
+  "ۃ": 20,
+  "ی": 6,
+  "ے": 18,
+  "ۓ": 12
+}