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