WeTextProcessing 1.0.1__py3-none-any.whl → 1.0.2__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: WeTextProcessing
3
- Version: 1.0.1
3
+ Version: 1.0.2
4
4
  Summary: WeTextProcessing, including TN & ITN
5
5
  Home-page: https://github.com/wenet-e2e/WeTextProcessing
6
6
  Author: Zhendong Peng, Xingchen Song
@@ -1,7 +1,7 @@
1
1
  itn/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
2
2
  itn/__main__.py,sha256=jFh8bEB_lC5y7ab9VMqAxWRaI8D-SpBSTiHfMJC1b10,65
3
3
  itn/main.py,sha256=NnT9Sh3VTEI0sX_DO9IGVsXCWtZyfRbzj9Sj_6cBxqM,2610
4
- itn/zh_itn_tagger.fst,sha256=CtbG9WnTvHZFwtKN4Y2-1IViI5NEWLDepbSVp91LNDU,1602718
4
+ itn/zh_itn_tagger.fst,sha256=32FSrQ6gcFYNTUYaHinnrdaMZUpAwuDmvu-EPnki8aI,1172366
5
5
  itn/zh_itn_verbalizer.fst,sha256=pHXRUfzls2UmWwTmHHhYmBWMusIfWpU3I7IwxeRjn28,119018
6
6
  itn/chinese/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
7
7
  itn/chinese/inverse_normalizer.py,sha256=9GpVP7_BCBoCIpoZkPa8aq-n7M56GhY9l4mp3jUGwpM,3563
@@ -26,7 +26,7 @@ itn/chinese/data/time/minute.tsv,sha256=R2HgErTDIq_rxxRwuEotdZFmDbBgZP2DE1Ejxp6A
26
26
  itn/chinese/data/time/noon.tsv,sha256=rWP0aMoTlQ7yEUcav_wXfGLBz2sHMwT37eLmDKZ16X0,72
27
27
  itn/chinese/data/time/second.tsv,sha256=fBb-Gt3U0ehbVnM51ngS8n_eEz2bqdpLJvMY7pdeLUg,849
28
28
  itn/chinese/rules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
29
- itn/chinese/rules/cardinal.py,sha256=Y9T-qPfIxuiFU6UT_v8vwAMvNAtzv3ofpBd6OWEvcsg,8006
29
+ itn/chinese/rules/cardinal.py,sha256=pFhQ934IqZH4isx7I8el2xvHtr0padu57xsZMCor8YU,7977
30
30
  itn/chinese/rules/char.py,sha256=wWnTfzJqE5j7kvEao9rKSN29OVFGNnL25MxS7PcfWEM,965
31
31
  itn/chinese/rules/date.py,sha256=8pB_S9BFKYd5rXGxzfjAcas-ecLM4dUnhNIsp_vZgI0,2447
32
32
  itn/chinese/rules/fraction.py,sha256=jGhKx91TtscqPFwDtqaI0zeMCAsCFA68KPCWBXtT030,2030
@@ -48,15 +48,15 @@ tn/main.py,sha256=Q45id3b2g71MPRLnaHpo8iWPc38MeyZKigNd5FinNvI,3578
48
48
  tn/processor.py,sha256=CUmJ7B0OyweByf7U0yi2TYqBbEhhWTcqs03_0XhTosg,5012
49
49
  tn/token_parser.py,sha256=nsTYzug-gq2HYnTJHja_HXntoRVX3gITQAlI9z8WvWU,4487
50
50
  tn/utils.py,sha256=lJLuW2jkobgXCyNYl29zhtyb3B80CS7Pqz7zqHRVr4c,2792
51
- tn/zh_tn_tagger.fst,sha256=zZ7zLr-Y774X3lb9bnmUv9Fs3Gv-LXa44X0rMFL6a9g,3477714
51
+ tn/zh_tn_tagger.fst,sha256=vIfJeXdWDvOSwLVmuNDeWktIq29UkcWUfbKjBnMY3cA,3479454
52
52
  tn/zh_tn_verbalizer.fst,sha256=VoZnjew7YiDRoDC6TgDHKXhrkcSGOz030Pnqad8JhcE,558366
53
53
  tn/chinese/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
54
54
  tn/chinese/normalizer.py,sha256=4FiYRyx_cfzTL77gonlcpSyGxFbZbVdupFRRLx-J2UQ,3851
55
55
  tn/chinese/data/char/charset_extension.tsv,sha256=kUxQXkh5k1jeYpkNplRBlIZ6vzCUjNn23RNku5XPGvk,24
56
56
  tn/chinese/data/char/charset_national_standard_2013_8105.tsv,sha256=7GLEH98Fh_T2L_UhgD8LOQzPps7XBbT3ZM0KKK1etAQ,32616
57
57
  tn/chinese/data/char/fullwidth_to_halfwidth.tsv,sha256=Xs9kwylqrJp-Ew5Z_31686L2elA8r24q0FYKqPfNRe4,570
58
- tn/chinese/data/char/punctuations_zh.tsv,sha256=TpC5Ncogj0uJ980VRkpYq3HsxqV_MENsY-eLTRkkMTU,288
59
- tn/chinese/data/char/traditional_to_simple.tsv,sha256=hqE4gU1wmdhhWBPDhmz5Oy-kJdJCxDnEYWefCkEezzQ,25160
58
+ tn/chinese/data/char/punctuations_zh.tsv,sha256=8X7rzt0P4AWyp9EWA_xkgwFf1dk8Z-ME6FTuVoSh9qw,292
59
+ tn/chinese/data/char/traditional_to_simple.tsv,sha256=0FXZVJjOtSpGpzkcc1KcQRxnBRtPcWVrqgzAYKGXLPw,25168
60
60
  tn/chinese/data/date/d.tsv,sha256=GrIfCvNeZho4jZssTbtzJoecE5HEt7PG4t_WdWfJvdc,394
61
61
  tn/chinese/data/date/dd.tsv,sha256=oPLQNhJ08cOUtqI_uM1aQ8by4kOv4zkmd-kux2kMb_Q,403
62
62
  tn/chinese/data/date/m.tsv,sha256=KELO_dRSedVfNfqsjhPJRrh8SofOYKcPcpi3a-DsZBc,117
@@ -204,9 +204,9 @@ tn/english/test/time_test.py,sha256=4E_PS-D5caTUZgrI-UL7q0aoqmtD8np7yeXUkGyc1Qo,
204
204
  tn/english/test/utils.py,sha256=aCZH5BL0dghGjemhVwfISBUxLFMG_ceMzwzuOb5ht28,1094
205
205
  tn/english/test/whitelist_test.py,sha256=fnlpnwiDgQWsl5ONZklWXEyLQoUSuwhdowcV7a8fXvw,1023
206
206
  tn/english/test/word_test.py,sha256=ACguloXPl4Ttw8fj9F_wvr1coaQAoj_MLOJ74wyy-WY,954
207
- WeTextProcessing-1.0.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
208
- WeTextProcessing-1.0.1.dist-info/METADATA,sha256=z8PobLYspZTnYiLE4NiEO4SfAAjbAby7olwWRQ8p-gs,5178
209
- WeTextProcessing-1.0.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
210
- WeTextProcessing-1.0.1.dist-info/entry_points.txt,sha256=iAd8tFSNA8AY5fUECPlk9KaDFC3ISvDjoKAZVsCWPjE,61
211
- WeTextProcessing-1.0.1.dist-info/top_level.txt,sha256=6NasE_UheQezX9_0V3MbiOSnTQpvM_funMjv4wpMGgA,7
212
- WeTextProcessing-1.0.1.dist-info/RECORD,,
207
+ WeTextProcessing-1.0.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
208
+ WeTextProcessing-1.0.2.dist-info/METADATA,sha256=vINHY2ibaBLdN56EpTFgkk5Wn-jde8RfYy1gS6qnn7A,5178
209
+ WeTextProcessing-1.0.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
210
+ WeTextProcessing-1.0.2.dist-info/entry_points.txt,sha256=iAd8tFSNA8AY5fUECPlk9KaDFC3ISvDjoKAZVsCWPjE,61
211
+ WeTextProcessing-1.0.2.dist-info/top_level.txt,sha256=6NasE_UheQezX9_0V3MbiOSnTQpvM_funMjv4wpMGgA,7
212
+ WeTextProcessing-1.0.2.dist-info/RECORD,,
@@ -69,7 +69,7 @@ class Cardinal(Processor):
69
69
  | add_weight(addzero**2, 1.0)))
70
70
  # 一千一百一十一 => 1111, 一千零一十一 => 1011, 一千零一 => 1001
71
71
  # 一千一 => 1100, 一千 => 1000
72
- thousand = ((hundred | teen | tens | digits) + delete('千') +
72
+ thousand = (digit + delete('千') +
73
73
  (hundred
74
74
  | add_weight(zero + (tens | teen), 0.1)
75
75
  | add_weight(addzero + zero + digit, 0.5)
@@ -78,7 +78,7 @@ class Cardinal(Processor):
78
78
  # 10001111, 1001111, 101111, 11111, 10111, 10011, 10001, 10000
79
79
  if self.enable_million:
80
80
  ten_thousand = (
81
- (thousand | hundred | teen | tens | digits) + delete('万') +
81
+ (thousand | hundred | teen | tens | digit) + delete('万') +
82
82
  (thousand
83
83
  | add_weight(zero + hundred, 0.1)
84
84
  | add_weight(addzero + zero + (tens | teen), 0.5)
@@ -87,7 +87,7 @@ class Cardinal(Processor):
87
87
  | add_weight(addzero**4, 1.0)))
88
88
  else:
89
89
  ten_thousand = (
90
- (teen | tens | digits) + delete('万') +
90
+ (teen | tens | digit) + delete('万') +
91
91
  (thousand
92
92
  | add_weight(zero + hundred, 0.1)
93
93
  | add_weight(addzero + zero + (tens | teen), 0.5)
itn/zh_itn_tagger.fst CHANGED
Binary file
@@ -12,6 +12,7 @@
12
12
  、
13
13
  。
14
14
  〃
15
+ 《
15
16
  》
16
17
  「
17
18
  」
@@ -3143,3 +3143,4 @@
3143
3143
  龔 龚
3144
3144
  龕 龛
3145
3145
  龜 龟
3146
+ 後 后
tn/zh_tn_tagger.fst CHANGED
Binary file