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