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