add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 37, "</s>": 38}

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 @@
+{"ا": 1, "ب": 2, "ت": 3, "ث": 4, "ج": 5, "ح": 6, "خ": 7, "د": 8, "ذ": 9, "ر": 10, "ز": 11, "س": 12, "ش": 13, "ص": 14, "ض": 15, "ط": 16, "ظ": 17, "ع": 18, "غ": 19, "ف": 20, "ق": 21, "ل": 22, "م": 23, "ن": 24, "ه": 25, "و": 26, "ى": 27, "ٓ": 28, "پ": 29, "چ": 30, "ژ": 31, "ک": 32, "گ": 33, "ی": 34, "|": 0, "[UNK]": 35, "[PAD]": 36}