add tokenizer

runs/Oct17_05-43-15_e6cad45de4b8/events.out.tfevents.1665985956.e6cad45de4b8.95.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab68a8b120c47e3dbf30afaa0db08135822158803a3e571052055bc4e0cf733
-size 5060
+oid sha256:ee97845805357d852644966fa9393c3c3e71b1fbab78c412f3c117924b9320bd
+size 8268

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 @@
+{"\n": 0, "0": 2, "1": 3, "2": 4, "3": 5, "4": 6, "5": 7, "6": 8, "7": 9, "8": 10, "9": 11, "a": 12, "b": 13, "c": 14, "h": 15, "l": 16, "m": 17, "n": 18, "p": 19, "s": 20, "t": 21, "z": 22, "ㄱ": 23, "ㄲ": 24, "ㄴ": 25, "ㄵ": 26, "ㄶ": 27, "ㄷ": 28, "ㄸ": 29, "ㄹ": 30, "ㄺ": 31, "ㄻ": 32, "ㄼ": 33, "ㅀ": 34, "ㅁ": 35, "ㅂ": 36, "ㅃ": 37, "ㅄ": 38, "ㅅ": 39, "ㅆ": 40, "ㅇ": 41, "ㅈ": 42, "ㅉ": 43, "ㅊ": 44, "ㅋ": 45, "ㅌ": 46, "ㅍ": 47, "ㅎ": 48, "ㅏ": 49, "ㅐ": 50, "ㅑ": 51, "ㅒ": 52, "ㅓ": 53, "ㅔ": 54, "ㅕ": 55, "ㅖ": 56, "ㅗ": 57, "ㅘ": 58, "ㅙ": 59, "ㅚ": 60, "ㅛ": 61, "ㅜ": 62, "ㅝ": 63, "ㅞ": 64, "ㅟ": 65, "ㅠ": 66, "ㅡ": 67, "ㅢ": 68, "ㅣ": 69, "，": 70, "|": 1, "[UNK]": 71, "[PAD]": 72}