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