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