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 @@
+{"h": 0, "r": 1, "v": 2, "i": 3, "x": 4, "d": 5, "m": 6, "k": 7, "z": 8, "y": 9, "j": 10, "t": 11, "s": 12, "g": 13, "b": 14, "p": 15, "u": 16, "w": 18, "f": 19, "o": 20, "c": 21, "n": 22, "l": 23, "a": 24, "e": 25, "|": 17, "[UNK]": 26, "[PAD]": 27}