add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 35, "</s>": 36}

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 @@
+{"r": 0, "c": 1, "ğ": 2, "q": 3, "ç": 4, "d": 5, "j": 6, "f": 7, "i": 8, "ö": 9, "t": 10, "z": 11, "u": 12, "o": 13, "h": 14, "k": 15, "v": 16, "w": 17, "ı": 18, "y": 19, "l": 20, "ü": 21, "p": 22, "m": 23, "ş": 24, "a": 26, "s": 27, "b": 28, "n": 29, "e": 30, "x": 31, "g": 32, "|": 25, "[UNK]": 33, "[PAD]": 34}