add tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 67,
+  "<s>": 66
+}

special_tokens_map.json

@@ -1 +1,22 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
+{
+  "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

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

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