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