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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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