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