Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 86,
+  "<s>": 85
+}

special_tokens_map.json

@@ -0,0 +1,50 @@
+{
+  "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
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "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 +1,13 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "ASR/Finetuning",
+  "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 +1,87 @@
+{
+  "[PAD]": 84,
+  "[UNK]": 83,
+  "`": 1,
+  "|": 0,
+  "،": 2,
+  "ؑ": 3,
+  "ؓ": 4,
+  "ؔ": 5,
+  "؛": 6,
+  "؟": 7,
+  "ء": 8,
+  "آ": 9,
+  "أ": 10,
+  "ؤ": 11,
+  "ئ": 12,
+  "ا": 13,
+  "ب": 14,
+  "ت": 15,
+  "ث": 16,
+  "ج": 17,
+  "ح": 18,
+  "خ": 19,
+  "د": 20,
+  "ذ": 21,
+  "ر": 22,
+  "ز": 23,
+  "س": 24,
+  "ش": 25,
+  "ص": 26,
+  "ض": 27,
+  "ط": 28,
+  "ظ": 29,
+  "ع": 30,
+  "غ": 31,
+  "ف": 32,
+  "ق": 33,
+  "ك": 34,
+  "ل": 35,
+  "م": 36,
+  "ن": 37,
+  "ه": 38,
+  "و": 39,
+  "ى": 40,
+  "ي": 41,
+  "ً": 42,
+  "َ": 43,
+  "ُ": 44,
+  "ِ": 45,
+  "ّ": 46,
+  "ْ": 47,
+  "ٓ": 48,
+  "ٔ": 49,
+  "ٗ": 50,
+  "ٰ": 51,
+  "ٹ": 52,
+  "پ": 53,
+  "چ": 54,
+  "ڈ": 55,
+  "ڑ": 56,
+  "ژ": 57,
+  "ک": 58,
+  "گ": 59,
+  "ں": 60,
+  "ھ": 61,
+  "ہ": 62,
+  "ۂ": 63,
+  "ۃ": 64,
+  "ی": 65,
+  "ے": 66,
+  "ۓ": 67,
+  "۔": 68,
+  "’": 69,
+  "…": 70,
+  "ﭨ": 71,
+  "ﮭ": 72,
+  "ﮯ": 73,
+  "ﯾ": 74,
+  "ﷲ": 75,
+  "ﷺ": 76,
+  "ﺗ": 77,
+  "ﺘ": 78,
+  "ﺩ": 79,
+  "ﺲ": 80,
+  "ﻧ": 81,
+  "ﻮ": 82
+}