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

vocab.json

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