Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 110,
+  "<s>": 109
+}

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 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "107": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "108": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "ur",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,113 @@
+{
+  "ur": {
+    "0": 12,
+    "1": 48,
+    "2": 23,
+    "3": 24,
+    "4": 86,
+    "5": 58,
+    "6": 73,
+    "7": 59,
+    "8": 65,
+    "9": 105,
+    "[PAD]": 108,
+    "[UNK]": 107,
+    "`": 100,
+    "a": 28,
+    "b": 4,
+    "c": 66,
+    "d": 33,
+    "e": 69,
+    "f": 3,
+    "g": 82,
+    "h": 38,
+    "i": 20,
+    "k": 92,
+    "l": 6,
+    "m": 74,
+    "n": 99,
+    "o": 83,
+    "p": 93,
+    "r": 36,
+    "s": 45,
+    "t": 56,
+    "u": 44,
+    "v": 32,
+    "w": 41,
+    "x": 101,
+    "|": 5,
+    "": 85,
+    "­": 70,
+    "ء": 62,
+    "آ": 77,
+    "ؤ": 96,
+    "إ": 13,
+    "ئ": 81,
+    "ا": 79,
+    "ب": 46,
+    "ت": 31,
+    "ث": 47,
+    "ج": 95,
+    "ح": 7,
+    "خ": 8,
+    "د": 88,
+    "ذ": 94,
+    "ر": 1,
+    "ز": 98,
+    "س": 11,
+    "ش": 10,
+    "ص": 68,
+    "ض": 49,
+    "ط": 55,
+    "ظ": 63,
+    "ع": 9,
+    "غ": 60,
+    "ـ": 61,
+    "ف": 14,
+    "ق": 90,
+    "ك": 54,
+    "ل": 22,
+    "م": 106,
+    "ن": 0,
+    "ه": 103,
+    "و": 15,
+    "ي": 64,
+    "ٸ": 2,
+    "ٹ": 75,
+    "پ": 39,
+    "چ": 76,
+    "ڈ": 91,
+    "ڑ": 21,
+    "ژ": 40,
+    "ک": 29,
+    "گ": 51,
+    "ں": 53,
+    "ھ": 57,
+    "ہ": 97,
+    "ۂ": 52,
+    "ۃ": 19,
+    "ی": 16,
+    "ے": 104,
+    "ۓ": 26,
+    "۰": 25,
+    "۱": 17,
+    "۲": 27,
+    "۳": 72,
+    "۴": 87,
+    "۵": 35,
+    "۶": 50,
+    "۷": 84,
+    "۸": 71,
+    "۹": 102,
+    "​": 89,
+    "‌": 18,
+    "‍": 43,
+    "‎": 42,
+    "‏": 80,
+    "‫": 37,
+    "‬": 30,
+    "⁦": 67,
+    "ﮟ": 78,
+    "ﷲ": 34
+  }
+}