BatchalignHK 0.7.19.post1__tar.gz → 0.7.19.post3__tar.gz

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.
Files changed (124) hide show
  1. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/BatchalignHK.egg-info/PKG-INFO +5 -3
  2. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/BatchalignHK.egg-info/SOURCES.txt +1 -0
  3. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/BatchalignHK.egg-info/requires.txt +2 -1
  4. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/PKG-INFO +5 -3
  5. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/analysis/eval.py +15 -0
  6. batchalignhk-0.7.19.post3/batchalign/utils/names.py +6684 -0
  7. batchalignhk-0.7.19.post3/batchalign/version +3 -0
  8. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/setup.py +1 -1
  9. batchalignhk-0.7.19.post1/batchalign/version +0 -3
  10. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/BatchalignHK.egg-info/dependency_links.txt +0 -0
  11. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/BatchalignHK.egg-info/entry_points.txt +0 -0
  12. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/BatchalignHK.egg-info/top_level.txt +0 -0
  13. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/LICENSE +0 -0
  14. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/MANIFEST.in +0 -0
  15. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/README.md +0 -0
  16. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/__init__.py +0 -0
  17. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/__main__.py +0 -0
  18. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/cli/__init__.py +0 -0
  19. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/cli/cli.py +0 -0
  20. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/cli/dispatch.py +0 -0
  21. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/constants.py +0 -0
  22. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/document.py +0 -0
  23. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/errors.py +0 -0
  24. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/__init__.py +0 -0
  25. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/base.py +0 -0
  26. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/chat/__init__.py +0 -0
  27. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/chat/file.py +0 -0
  28. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/chat/generator.py +0 -0
  29. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/chat/lexer.py +0 -0
  30. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/chat/parser.py +0 -0
  31. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/chat/utils.py +0 -0
  32. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/textgrid/__init__.py +0 -0
  33. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/textgrid/file.py +0 -0
  34. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/textgrid/generator.py +0 -0
  35. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/formats/textgrid/parser.py +0 -0
  36. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/__init__.py +0 -0
  37. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/resolve.py +0 -0
  38. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/speaker/__init__.py +0 -0
  39. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/speaker/config.yaml +0 -0
  40. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/speaker/infer.py +0 -0
  41. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/speaker/utils.py +0 -0
  42. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/training/__init__.py +0 -0
  43. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/training/run.py +0 -0
  44. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/training/utils.py +0 -0
  45. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utils.py +0 -0
  46. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utterance/__init__.py +0 -0
  47. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utterance/cantonese_infer.py +0 -0
  48. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utterance/dataset.py +0 -0
  49. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utterance/execute.py +0 -0
  50. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utterance/infer.py +0 -0
  51. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utterance/prep.py +0 -0
  52. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/utterance/train.py +0 -0
  53. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/wave2vec/__init__.py +0 -0
  54. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/wave2vec/infer_fa.py +0 -0
  55. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/whisper/__init__.py +0 -0
  56. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/whisper/infer_asr.py +0 -0
  57. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/models/whisper/infer_fa.py +0 -0
  58. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/__init__.py +0 -0
  59. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/analysis/__init__.py +0 -0
  60. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/__init__.py +0 -0
  61. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/num2chinese.py +0 -0
  62. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/oai_whisper.py +0 -0
  63. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/rev.py +0 -0
  64. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/tencent.py +0 -0
  65. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/utils.py +0 -0
  66. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/whisper.py +0 -0
  67. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/asr/whisperx.py +0 -0
  68. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/base.py +0 -0
  69. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/__init__.py +0 -0
  70. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/cleanup.py +0 -0
  71. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
  72. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/parse_support.py +0 -0
  73. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/retrace.py +0 -0
  74. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
  75. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
  76. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/cleanup/support/test.test +0 -0
  77. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/dispatch.py +0 -0
  78. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/fa/__init__.py +0 -0
  79. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/fa/wave2vec_fa.py +0 -0
  80. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/fa/whisper_fa.py +0 -0
  81. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
  82. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/coref.py +0 -0
  83. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
  84. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/fr/apm.py +0 -0
  85. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/fr/apmn.py +0 -0
  86. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
  87. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
  88. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/morphosyntax/ud.py +0 -0
  89. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/pipeline.py +0 -0
  90. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/speaker/__init__.py +0 -0
  91. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
  92. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/translate/__init__.py +0 -0
  93. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/translate/gtrans.py +0 -0
  94. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/translate/seamless.py +0 -0
  95. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/translate/utils.py +0 -0
  96. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/utr/__init__.py +0 -0
  97. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/utr/rev_utr.py +0 -0
  98. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/utr/utils.py +0 -0
  99. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/utr/whisper_utr.py +0 -0
  100. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/utterance/__init__.py +0 -0
  101. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
  102. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/__init__.py +0 -0
  103. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/conftest.py +0 -0
  104. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
  105. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
  106. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
  107. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
  108. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
  109. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
  110. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
  111. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
  112. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
  113. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
  114. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
  115. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
  116. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/fixures.py +0 -0
  117. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/test_pipeline.py +0 -0
  118. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
  119. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/tests/test_document.py +0 -0
  120. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/utils/__init__.py +0 -0
  121. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/utils/config.py +0 -0
  122. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/utils/dp.py +0 -0
  123. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/batchalign/utils/utils.py +0 -0
  124. {batchalignhk-0.7.19.post1 → batchalignhk-0.7.19.post3}/setup.cfg +0 -0
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.4
2
2
  Name: BatchalignHK
3
- Version: 0.7.19.post1
3
+ Version: 0.7.19.post3
4
4
  Summary: Python Speech Language Sample Analysis
5
5
  Author: Brian MacWhinney, Houjun Liu
6
6
  Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -35,7 +35,8 @@ Requires-Dist: tiktoken
35
35
  Requires-Dist: blobfile
36
36
  Requires-Dist: sentencepiece
37
37
  Requires-Dist: tencentcloud-sdk-python-common
38
- Requires-Dist: tencentcloud-sdk-python-asrgoogletrans
38
+ Requires-Dist: tencentcloud-sdk-python-asr
39
+ Requires-Dist: googletrans
39
40
  Requires-Dist: openai-whisper>=20240930
40
41
  Provides-Extra: dev
41
42
  Requires-Dist: pytest; extra == "dev"
@@ -49,6 +50,7 @@ Dynamic: author-email
49
50
  Dynamic: classifier
50
51
  Dynamic: description
51
52
  Dynamic: description-content-type
53
+ Dynamic: license-file
52
54
  Dynamic: provides-extra
53
55
  Dynamic: requires-dist
54
56
  Dynamic: summary
@@ -117,4 +117,5 @@ batchalign/tests/pipelines/fa/test_fa_pipeline.py
117
117
  batchalign/utils/__init__.py
118
118
  batchalign/utils/config.py
119
119
  batchalign/utils/dp.py
120
+ batchalign/utils/names.py
120
121
  batchalign/utils/utils.py
@@ -25,7 +25,8 @@ tiktoken
25
25
  blobfile
26
26
  sentencepiece
27
27
  tencentcloud-sdk-python-common
28
- tencentcloud-sdk-python-asrgoogletrans
28
+ tencentcloud-sdk-python-asr
29
+ googletrans
29
30
  openai-whisper>=20240930
30
31
 
31
32
  [dev]
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.4
2
2
  Name: BatchalignHK
3
- Version: 0.7.19.post1
3
+ Version: 0.7.19.post3
4
4
  Summary: Python Speech Language Sample Analysis
5
5
  Author: Brian MacWhinney, Houjun Liu
6
6
  Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -35,7 +35,8 @@ Requires-Dist: tiktoken
35
35
  Requires-Dist: blobfile
36
36
  Requires-Dist: sentencepiece
37
37
  Requires-Dist: tencentcloud-sdk-python-common
38
- Requires-Dist: tencentcloud-sdk-python-asrgoogletrans
38
+ Requires-Dist: tencentcloud-sdk-python-asr
39
+ Requires-Dist: googletrans
39
40
  Requires-Dist: openai-whisper>=20240930
40
41
  Provides-Extra: dev
41
42
  Requires-Dist: pytest; extra == "dev"
@@ -49,6 +50,7 @@ Dynamic: author-email
49
50
  Dynamic: classifier
50
51
  Dynamic: description
51
52
  Dynamic: description-content-type
53
+ Dynamic: license-file
52
54
  Dynamic: provides-extra
53
55
  Dynamic: requires-dist
54
56
  Dynamic: summary
@@ -10,6 +10,7 @@ from batchalign.pipelines.asr.utils import *
10
10
  from batchalign.utils.config import config_read
11
11
 
12
12
  from batchalign.utils.dp import align, ExtraType, Extra, Match
13
+ from batchalign.utils.names import names
13
14
 
14
15
  import logging
15
16
  L = logging.getLogger("batchalign")
@@ -26,6 +27,20 @@ def conform(x):
26
27
  elif "postwar" == i.strip():
27
28
  result.append("post")
28
29
  result.append("war")
30
+ elif "postwar" == i.strip():
31
+ result.append("post")
32
+ result.append("war")
33
+ elif i.strip() in names:
34
+ result.append("name")
35
+ elif "dunno" == i.strip():
36
+ result.append("don't")
37
+ result.append("know")
38
+ elif "wanna" == i.strip():
39
+ result.append("want")
40
+ result.append("to")
41
+ elif "gotta" == i.strip():
42
+ result.append("got")
43
+ result.append("to")
29
44
  elif "farmhouse" == i.strip():
30
45
  result.append("farm")
31
46
  result.append("house")