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