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