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