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