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