Ayaka
/

bart-base-cantonese

feature-extraction

Inference Endpoints

Model card Files Files and versions Community

Ayaka commited on Oct 26, 2022

Commit

05379c1

•

1 Parent(s): 8348bab

add tokenizer

Files changed (2) hide show

tokenizer_config.json +1 -1
vocab.txt +9 -8

tokenizer_config.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "name_or_path": "./vocab-bart-base-cantonese.txt",
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "name_or_path": "vocab-bart-base-cantonese.txt",
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

vocab.txt CHANGED Viewed

@@ -21,6 +21,7 @@
 乪
 乸
 亍
 佮
 侲
 冚
@@ -28,6 +29,7 @@
 剒
 劖
 卼
 厹
 厾
 吔
@@ -80,6 +82,7 @@
 埞
 埲
 奀
 嬡
 嬲
 孭
@@ -95,9 +98,6 @@
 忳
 愎
 愩
-愾
-戇
-戙
 [UNK]
 [CLS]
 [SEP]
@@ -12386,12 +12386,16 @@ fishbase
 ##🔥
 ##😂
 ##😎
 戥
 戽
 扚
 扠
 扤
 扲
 扻
 扽
 抆
@@ -12439,9 +12443,7 @@ fishbase
 攋
 攰
 斲
-昅
 曱
-柙
 栢
 梘
 棖
@@ -12478,6 +12480,7 @@ fishbase
 燶
 爨
 猁
 獌
 瑒
 甖
@@ -12536,6 +12539,7 @@ fishbase
 蝻
 螆
 蠋
 裇
 褦
 褸
@@ -12567,7 +12571,6 @@ fishbase
 鋭
 錔
 錡
-鍚
 鍠
 鎅
 鎝
@@ -12576,7 +12579,6 @@ fishbase
 閂
 閪
 韞
-韮
 頇
 餲
 餸
@@ -12654,6 +12656,5 @@ fishbase
 𨈇
 𨋢
 𨳒
-𨶙
 𩓥
 𪘲

 乪
 乸
 亍
+仼
 佮
 侲
 冚
 剒
 劖
 卼
+厠
 厹
 厾
 吔
 埞
 埲
 奀
+妺
 嬡
 嬲
 孭
 忳
 愎
 愩
 [UNK]
 [CLS]
 [SEP]
 ##🔥
 ##😂
 ##😎
+愾
+戇
+戙
 戥
 戽
 扚
 扠
 扤
 扲
+扺
 扻
 扽
 抆
 攋
 攰
 斲
 曱
 栢
 梘
 棖
 燶
 爨
 猁
+猢
 獌
 瑒
 甖
 蝻
 螆
 蠋
+袓
 裇
 褦
 褸
 鋭
 錔
 錡
 鍠
 鎅
 鎝
 閂
 閪
 韞
 頇
 餲
 餸
 𨈇
 𨋢
 𨳒
 𩓥
 𪘲