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