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