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