Upload tokenizer

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 70,
+  "<s>": 69,
+  "[PAD]": 68,
+  "[UNK]": 67
+}

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 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "67": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "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",
+  "tokenizer_file": null,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,71 @@
+{
+  "[PAD]": 68,
+  "[UNK]": 67,
+  "_": 1,
+  "e": 2,
+  "g": 3,
+  "t": 4,
+  "|": 0,
+  "«": 5,
+  "»": 6,
+  "،": 7,
+  "؛": 8,
+  "؟": 9,
+  "ء": 10,
+  "آ": 11,
+  "أ": 12,
+  "ؤ": 13,
+  "إ": 14,
+  "ئ": 15,
+  "ا": 16,
+  "ب": 17,
+  "ة": 18,
+  "ت": 19,
+  "ث": 20,
+  "ج": 21,
+  "ح": 22,
+  "خ": 23,
+  "د": 24,
+  "ذ": 25,
+  "ر": 26,
+  "ز": 27,
+  "س": 28,
+  "ش": 29,
+  "ص": 30,
+  "ض": 31,
+  "ط": 32,
+  "ظ": 33,
+  "ع": 34,
+  "غ": 35,
+  "ـ": 36,
+  "ف": 37,
+  "ق": 38,
+  "ك": 39,
+  "ل": 40,
+  "م": 41,
+  "ن": 42,
+  "ه": 43,
+  "و": 44,
+  "ى": 45,
+  "ي": 46,
+  "ً": 47,
+  "ٌ": 48,
+  "ٍ": 49,
+  "َ": 50,
+  "ُ": 51,
+  "ِ": 52,
+  "ّ": 53,
+  "ْ": 54,
+  "ٰ": 55,
+  "چ": 56,
+  "ڨ": 57,
+  "ک": 58,
+  "ھ": 59,
+  "ی": 60,
+  "ۖ": 61,
+  "ۚ": 62,
+  "—": 63,
+  "☭": 64,
+  "ﺃ": 65,
+  "ﻻ": 66
+}