add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 89, "</s>": 90}

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 @@
+{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "،": 26, "؛": 27, "؟": 28, "ء": 29, "آ": 30, "أ": 31, "ؤ": 32, "إ": 33, "ئ": 34, "ا": 35, "ب": 36, "ة": 37, "ت": 38, "ث": 39, "ج": 40, "ح": 41, "خ": 42, "د": 43, "ذ": 44, "ر": 45, "ز": 46, "س": 47, "ش": 48, "ص": 49, "ض": 50, "ط": 51, "ظ": 52, "ع": 53, "غ": 54, "ـ": 55, "ف": 56, "ق": 57, "ك": 58, "ل": 59, "م": 60, "ن": 61, "ه": 62, "و": 63, "ى": 64, "ي": 65, "ً": 66, "ٌ": 67, "ٍ": 68, "َ": 69, "ُ": 70, "ِ": 71, "ّ": 72, "ْ": 73, "ٰ": 74, "چ": 75, "ڨ": 76, "ک": 77, "ھ": 78, "ی": 79, "ۖ": 80, "ۗ": 81, "ۘ": 82, "ۚ": 83, "ۛ": 84, "ﺃ": 85, "ﻻ": 86, "|": 0, "[UNK]": 87, "[PAD]": 88}