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