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