Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 35,
+  "<s>": 34
+}

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": {
+    "32": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "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": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,36 @@
+{
+  "[PAD]": 33,
+  "[UNK]": 32,
+  "|": 0,
+  "ء": 1,
+  "ا": 2,
+  "ب": 3,
+  "ة": 4,
+  "ت": 5,
+  "ث": 6,
+  "ج": 7,
+  "ح": 8,
+  "خ": 9,
+  "د": 10,
+  "ذ": 11,
+  "ر": 12,
+  "ز": 13,
+  "س": 14,
+  "ش": 15,
+  "ص": 16,
+  "ض": 17,
+  "ط": 18,
+  "ظ": 19,
+  "ع": 20,
+  "غ": 21,
+  "ف": 22,
+  "ق": 23,
+  "ك": 24,
+  "ل": 25,
+  "م": 26,
+  "ن": 27,
+  "ه": 28,
+  "و": 29,
+  "ى": 30,
+  "ي": 31
+}