Upload tokenizer

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 +1,13 @@
+{
+  "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 +1,62 @@
+{
+  "/": 2,
+  "0": 21,
+  "1": 34,
+  "2": 49,
+  "7": 20,
+  "9": 50,
+  "[PAD]": 59,
+  "[UNK]": 58,
+  "_": 17,
+  "a": 19,
+  "c": 43,
+  "e": 6,
+  "f": 51,
+  "j": 40,
+  "l": 12,
+  "m": 48,
+  "o": 33,
+  "q": 0,
+  "r": 32,
+  "t": 14,
+  "u": 30,
+  "w": 47,
+  "|": 44,
+  "ء": 31,
+  "آ": 28,
+  "أ": 45,
+  "إ": 27,
+  "ئ": 23,
+  "ا": 35,
+  "ب": 46,
+  "ة": 9,
+  "ت": 56,
+  "ث": 7,
+  "ج": 11,
+  "ح": 5,
+  "خ": 29,
+  "د": 54,
+  "ذ": 10,
+  "ر": 52,
+  "ز": 55,
+  "س": 39,
+  "ش": 1,
+  "ص": 53,
+  "ض": 3,
+  "ط": 4,
+  "ظ": 38,
+  "ع": 24,
+  "غ": 22,
+  "ف": 25,
+  "ق": 42,
+  "ك": 41,
+  "ل": 57,
+  "م": 15,
+  "ن": 18,
+  "ه": 37,
+  "و": 26,
+  "ى": 13,
+  "ي": 16,
+  "ٱ": 36,
+  "ڤ": 8
+}