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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"g": 0, "z": 1, "2": 2, "m": 3, "r": 4, "4": 5, "k": 6, "c": 7, "q": 8, "h": 9, "w": 10, "3": 11, "p": 12, "b": 13, "v": 14, "1": 15, "0": 16, "y": 17, "l": 18, "6": 19, "d": 20, "u": 21, "o": 22, "j": 23, "9": 24, "t": 25, "i": 26, "n": 27, "a": 28, "e": 29, "'": 30, "x": 31, "5": 32, "s": 34, "8": 35, "f": 36, "|": 33, "[UNK]": 37, "[PAD]": 38}