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