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