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, "s": 1, "h": 2, "n": 3, "c": 4, "e": 5, "d": 6, "m": 7, "k": 8, "p": 9, "l": 10, "a": 11, "r": 12, "t": 13, "f": 14, "w": 15, "u": 16, "b": 18, "i": 19, "o": 20, "y": 21, "|": 17, "[UNK]": 22, "[PAD]": 23}