add tokenizer

added_tokens.json

@@ -1 +1,4 @@
-{"<s>": 73, "</s>": 74}
+{
+  "</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>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{
+  "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": " ", "name_or_path": "BakhtUllah123/xlsr_ur_training", "special_tokens_map_file": null, "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
+{
+  "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 @@
-{"!": 1, "\"": 2, "'": 3, ",": 4, "-": 5, ":": 6, "[PAD]": 72, "[UNK]": 71, "|": 0, "،": 7, "؟": 8, "ء": 9, "آ": 10, "أ": 11, "ؤ": 12, "ئ": 13, "ا": 14, "ب": 15, "ت": 16, "ث": 17, "ج": 18, "ح": 19, "خ": 20, "د": 21, "ذ": 22, "ر": 23, "ز": 24, "س": 25, "ش": 26, "ص": 27, "ض": 28, "ط": 29, "ظ": 30, "ع": 31, "غ": 32, "ف": 33, "ق": 34, "ل": 35, "م": 36, "ن": 37, "و": 38, "ى": 39, "ي": 40, "ً": 41, "َ": 42, "ُ": 43, "ِ": 44, "ّ": 45, "ٓ": 46, "ٔ": 47, "ٰ": 48, "ٹ": 49, "پ": 50, "چ": 51, "ڈ": 52, "ڑ": 53, "ژ": 54, "ک": 55, "گ": 56, "ں": 57, "ھ": 58, "ہ": 59, "ۂ": 60, "ۃ": 61, "ی": 62, "ے": 63, "ۓ": 64, "۔": 65, "‘": 66, "’": 67, "…": 68, "ﷲ": 69, "ﷺ": 70}
+{
+  "'": 1,
+  "[PAD]": 65,
+  "[UNK]": 64,
+  "|": 0,
+  "،": 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
+}