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