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 @@
+{"z": 0, "y": 1, "u": 2, "a": 3, "n": 4, "f": 5, "k": 6, "r": 7, "m": 8, "t": 9, "g": 10, "w": 11, "x": 12, "j": 13, "o": 14, "s": 15, "c": 17, "e": 18, "'": 19, "p": 20, "v": 21, "h": 22, "b": 23, "i": 24, "q": 25, "l": 26, "d": 27, "|": 16, "[UNK]": 28, "[PAD]": 29}