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