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