add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"،": 1, "؛": 2, "؟": 3, "ً": 4, "ٌ": 5, "ٍ": 6, "َ": 7, "ُ": 8, "ّ": 9, "ْ": 10, "ٰ": 11, "ۖ": 12, "ۗ": 13, "ۘ": 14, "ۚ": 15, "ۛ": 16, "—": 17, "…": 18, "☭": 19, "|": 0, "<unk>": 20, "<pad>": 21, "<s>": 22, "</s>": 23}