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