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