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