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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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