add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 43, "</s>": 44}

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 @@
+{"e": 1, "r": 2, "t": 3, "n": 4, "i": 5, "s": 6, "a": 7, "o": 8, "l": 9, "d": 10, "g": 11, "k": 12, "m": 13, "v": 14, "f": 15, "å": 16, "p": 17, "u": 18, "h": 19, "j": 20, "b": 21, "ø": 22, "y": 23, "æ": 24, "q": 25, "c": 26, "?": 27, "w": 28, "x": 29, "2": 30, "6": 31, "z": 32, "1": 33, "0": 34, "5": 35, "3": 36, "4": 37, "8": 38, "9": 39, "7": 40, "|": 0, "[UNK]": 41, "[PAD]": 42}