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 @@
+{"SH": 0, "G": 1, "U": 2, "CH": 3, "T": 4, "S": 5, "Q": 6, "A": 7, "P": 8, "O:": 9, "I:": 10, "U:": 11, "E": 12, "D": 13, "A:": 14, "Q:": 15, "K": 16, "B": 17, "Z": 18, "TS": 19, "Y": 20, "N!": 21, "J": 22, "R": 23, "F": 24, "O": 25, "I": 26, "KY": 27, "[UNK]": 28, "[PAD]": 29, " ": 30, "|": 31}