huyue012 commited on
Commit
74700ac
1 Parent(s): 6f362a7

add tokenizer

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
runs/Nov17_15-22-23_2ad13774ecf8/1637162659.814819/events.out.tfevents.1637162659.2ad13774ecf8.71.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6f041297ef2ead00bacdd26a6329283b04338fcd943a759d34f8b129ed4cdf
3
+ size 4594
runs/Nov17_15-22-23_2ad13774ecf8/events.out.tfevents.1637162659.2ad13774ecf8.71.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0460a420ff9a818293e170353e40e1c9c6ed0a1103103646d6ad2cbed29ac53
3
+ size 4503
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
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 CHANGED
@@ -1 +1 @@
1
- {"[": 0, "i": 1, "u": 2, "l": 3, "5": 4, "w": 5, "&": 6, "q": 7, "8": 8, "p": 9, "b": 10, "x": 11, "$": 12, "z": 13, "+": 15, "h": 16, "3": 17, "7": 18, "r": 19, "a": 20, "g": 21, "'": 22, "c": 23, "2": 24, "j": 25, "m": 26, "e": 27, "0": 28, "t": 29, "o": 30, "1": 31, "]": 32, "v": 33, ">": 34, "4": 35, "k": 36, "f": 37, "n": 38, "6": 39, "s": 40, "_": 41, "<": 42, "9": 43, "y": 44, "d": 45, "|": 14, "<unk>": 46, "<pad>": 47}
1
+ {"i": 0, "n": 1, "x": 2, "s": 3, "g": 4, "k": 5, "y": 6, "m": 7, "r": 8, "l": 9, "c": 10, "'": 11, "j": 12, "b": 13, "h": 14, "t": 15, "q": 16, "p": 17, "v": 18, "a": 19, "d": 21, "u": 22, "o": 23, "f": 24, "w": 25, "e": 26, "z": 27, "|": 20, "[UNK]": 28, "[PAD]": 29}