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