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