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, "p": 1, "n": 2, "h": 3, "r": 4, "g": 5, "w": 6, "c": 7, "e": 8, "u": 9, "f": 10, "l": 11, "a": 12, "y": 13, "b": 14, "k": 15, "q": 16, " ": 17, "m": 18, "s": 19, "x": 20, "j": 21, "t": 22, "o": 23, "i": 24, "'": 25, "d": 26, "v": 27, "|": 17, "[UNK]": 29, "[PAD]": 30}