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