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