add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 28, "</s>": 29}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"،": 1, "؟": 2, "آ": 3, "ا": 4, "ب": 5, "ت": 6, "ث": 7, "خ": 8, "د": 9, "ر": 10, "س": 11, "ص": 12, "ف": 13, "ق": 14, "ل": 15, "م": 16, "ن": 17, "و": 18, "ک": 19, "ں": 20, "ھ": 21, "ہ": 22, "ی": 23, "ے": 24, "۔": 25, "|": 0, "[UNK]": 26, "[PAD]": 27}