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