add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 46, "</s>": 47}

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 @@
+{"w": 0, "ë": 1, ")": 2, "g": 3, "o": 4, "é": 5, "h": 6, "ş": 7, "ı": 8, "ö": 9, "y": 10, "m": 11, "q": 12, "k": 13, "j": 14, "'": 15, "s": 16, "z": 17, "ğ": 18, "̇": 19, "r": 20, "û": 21, "(": 22, "ç": 23, "c": 25, "d": 26, "â": 27, "n": 28, "t": 29, "x": 30, "u": 31, "ü": 32, "a": 33, "l": 34, "î": 35, "…": 36, "’": 37, "p": 38, "v": 39, "e": 40, "i": 41, "b": 42, "f": 43, "|": 24, "[UNK]": 44, "[PAD]": 45}