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 @@
+{"w": 0, "c": 2, "z": 3, "g": 4, "r": 5, "y": 6, "_": 7, "i": 8, "x": 9, "e": 10, "t": 11, "'": 12, "q": 13, "f": 14, "o": 15, "s": 16, "h": 17, "a": 18, "v": 19, "l": 20, "n": 21, "m": 22, "d": 23, "p": 24, "u": 25, "b": 26, "j": 27, "k": 28, "|": 1, "[UNK]": 29, "[PAD]": 30}