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