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