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