add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"[PAD]": 0, "[UNK]": 1, "|": 2, "A": 3, "B": 4, "C": 5, "D": 6, "E": 7, "F": 8, "G": 9, "H": 10, "I": 11, "J": 12, "K": 13, "L": 14, "M": 15, "N": 16, "O": 17, "P": 18, "Q": 19, "R": 20, "S": 21, "T": 22, "U": 23, "V": 24, "W": 25, "X": 26, "Y": 27, "Z": 28, "Å": 29, "Ä": 30, "Ö": 31}