add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 40, "</s>": 41}

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

vocab.json

@@ -0,0 +1 @@
+{"ğ": 0, "v": 1, "̇": 2, "w": 3, "i": 4, "ç": 5, "y": 6, "l": 7, "d": 8, "p": 9, "c": 10, "ı": 11, "m": 12, "'": 13, "j": 14, "k": 15, "x": 16, "s": 17, "e": 18, "f": 19, "a": 20, "ş": 21, "î": 22, "ü": 23, "o": 24, "b": 25, "ë": 26, "q": 27, "ö": 28, "u": 29, "â": 30, "n": 31, "z": 32, "h": 33, "r": 34, "t": 35, "g": 37, "|": 36, "[UNK]": 38, "[PAD]": 39}