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