BatchalignHK 0.7.17.post16__tar.gz → 0.7.17.post17__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 (119) hide show
  1. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/BatchalignHK.egg-info/PKG-INFO +4 -2
  2. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/BatchalignHK.egg-info/requires.txt +1 -0
  3. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/PKG-INFO +4 -2
  4. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/asr/tencent.py +4 -1
  5. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/version +1 -1
  6. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/setup.py +1 -0
  7. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/BatchalignHK.egg-info/SOURCES.txt +0 -0
  8. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/BatchalignHK.egg-info/dependency_links.txt +0 -0
  9. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/BatchalignHK.egg-info/entry_points.txt +0 -0
  10. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/BatchalignHK.egg-info/top_level.txt +0 -0
  11. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/LICENSE +0 -0
  12. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/MANIFEST.in +0 -0
  13. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/README.md +0 -0
  14. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/__init__.py +0 -0
  15. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/__main__.py +0 -0
  16. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/cli/__init__.py +0 -0
  17. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/cli/cli.py +0 -0
  18. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/cli/dispatch.py +0 -0
  19. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/constants.py +0 -0
  20. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/document.py +0 -0
  21. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/errors.py +0 -0
  22. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/__init__.py +0 -0
  23. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/base.py +0 -0
  24. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/chat/__init__.py +0 -0
  25. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/chat/file.py +0 -0
  26. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/chat/generator.py +0 -0
  27. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/chat/lexer.py +0 -0
  28. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/chat/parser.py +0 -0
  29. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/chat/utils.py +0 -0
  30. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/textgrid/__init__.py +0 -0
  31. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/textgrid/file.py +0 -0
  32. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/textgrid/generator.py +0 -0
  33. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/formats/textgrid/parser.py +0 -0
  34. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/__init__.py +0 -0
  35. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/resolve.py +0 -0
  36. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/speaker/__init__.py +0 -0
  37. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/speaker/config.yaml +0 -0
  38. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/speaker/infer.py +0 -0
  39. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/speaker/utils.py +0 -0
  40. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/training/__init__.py +0 -0
  41. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/training/run.py +0 -0
  42. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/training/utils.py +0 -0
  43. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utils.py +0 -0
  44. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utterance/__init__.py +0 -0
  45. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utterance/cantonese_infer.py +0 -0
  46. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utterance/dataset.py +0 -0
  47. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utterance/execute.py +0 -0
  48. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utterance/infer.py +0 -0
  49. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utterance/prep.py +0 -0
  50. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/utterance/train.py +0 -0
  51. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/wave2vec/__init__.py +0 -0
  52. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/wave2vec/infer_fa.py +0 -0
  53. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/whisper/__init__.py +0 -0
  54. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/whisper/infer_asr.py +0 -0
  55. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/models/whisper/infer_fa.py +0 -0
  56. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/__init__.py +0 -0
  57. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/analysis/__init__.py +0 -0
  58. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/analysis/eval.py +0 -0
  59. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/asr/__init__.py +0 -0
  60. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/asr/num2chinese.py +0 -0
  61. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/asr/rev.py +0 -0
  62. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/asr/utils.py +0 -0
  63. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/asr/whisper.py +0 -0
  64. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/asr/whisperx.py +0 -0
  65. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/base.py +0 -0
  66. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/__init__.py +0 -0
  67. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/cleanup.py +0 -0
  68. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
  69. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/parse_support.py +0 -0
  70. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/retrace.py +0 -0
  71. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
  72. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
  73. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/cleanup/support/test.test +0 -0
  74. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/dispatch.py +0 -0
  75. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/fa/__init__.py +0 -0
  76. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/fa/wave2vec_fa.py +0 -0
  77. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/fa/whisper_fa.py +0 -0
  78. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
  79. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/coref.py +0 -0
  80. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
  81. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/fr/apm.py +0 -0
  82. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/fr/apmn.py +0 -0
  83. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
  84. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
  85. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/morphosyntax/ud.py +0 -0
  86. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/pipeline.py +0 -0
  87. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/speaker/__init__.py +0 -0
  88. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
  89. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/translate/__init__.py +0 -0
  90. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/translate/seamless.py +0 -0
  91. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/utr/__init__.py +0 -0
  92. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/utr/rev_utr.py +0 -0
  93. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/utr/utils.py +0 -0
  94. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/utr/whisper_utr.py +0 -0
  95. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/utterance/__init__.py +0 -0
  96. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
  97. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/__init__.py +0 -0
  98. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/conftest.py +0 -0
  99. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
  100. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
  101. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
  102. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
  103. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
  104. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
  105. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
  106. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
  107. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
  108. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
  109. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
  110. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
  111. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/fixures.py +0 -0
  112. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/test_pipeline.py +0 -0
  113. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
  114. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/tests/test_document.py +0 -0
  115. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/utils/__init__.py +0 -0
  116. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/utils/config.py +0 -0
  117. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/utils/dp.py +0 -0
  118. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/batchalign/utils/utils.py +0 -0
  119. {batchalignhk-0.7.17.post16 → batchalignhk-0.7.17.post17}/setup.cfg +0 -0
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.4
2
2
  Name: BatchalignHK
3
- Version: 0.7.17.post16
3
+ Version: 0.7.17.post17
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
@@ -15,6 +15,7 @@ Requires-Dist: torch>=2.6.0
15
15
  Requires-Dist: torchaudio
16
16
  Requires-Dist: hmmlearn==0.3.0
17
17
  Requires-Dist: eyed3
18
+ Requires-Dist: opencc-python-reimplemented
18
19
  Requires-Dist: pydub
19
20
  Requires-Dist: imblearn
20
21
  Requires-Dist: plotly>=5.3.0
@@ -47,6 +48,7 @@ Dynamic: author-email
47
48
  Dynamic: classifier
48
49
  Dynamic: description
49
50
  Dynamic: description-content-type
51
+ Dynamic: license-file
50
52
  Dynamic: provides-extra
51
53
  Dynamic: requires-dist
52
54
  Dynamic: summary
@@ -5,6 +5,7 @@ torch>=2.6.0
5
5
  torchaudio
6
6
  hmmlearn==0.3.0
7
7
  eyed3
8
+ opencc-python-reimplemented
8
9
  pydub
9
10
  imblearn
10
11
  plotly>=5.3.0
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.4
2
2
  Name: BatchalignHK
3
- Version: 0.7.17.post16
3
+ Version: 0.7.17.post17
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
@@ -15,6 +15,7 @@ Requires-Dist: torch>=2.6.0
15
15
  Requires-Dist: torchaudio
16
16
  Requires-Dist: hmmlearn==0.3.0
17
17
  Requires-Dist: eyed3
18
+ Requires-Dist: opencc-python-reimplemented
18
19
  Requires-Dist: pydub
19
20
  Requires-Dist: imblearn
20
21
  Requires-Dist: plotly>=5.3.0
@@ -47,6 +48,7 @@ Dynamic: author-email
47
48
  Dynamic: classifier
48
49
  Dynamic: description
49
50
  Dynamic: description-content-type
51
+ Dynamic: license-file
50
52
  Dynamic: provides-extra
51
53
  Dynamic: requires-dist
52
54
  Dynamic: summary
@@ -12,6 +12,9 @@ from batchalign.errors import *
12
12
 
13
13
  from batchalign.models import BertUtteranceModel, BertCantoneseUtteranceModel, resolve
14
14
 
15
+ from opencc import OpenCC
16
+ cc = OpenCC('s2hk')
17
+
15
18
  import time
16
19
  import pathlib
17
20
  import pycountry
@@ -113,7 +116,7 @@ class TencentEngine(BatchalignEngine):
113
116
  "type": "text",
114
117
  "ts": (j.OffsetStartMs+start)/1000,
115
118
  "end_ts": (j.OffsetEndMs+start)/1000,
116
- "value": j.Word
119
+ "value": cc.convert(j.Word)
117
120
  })
118
121
  turns.append({
119
122
  "elements": turn,
@@ -1,3 +1,3 @@
1
- 0.7.17-post.16
1
+ 0.7.17-post.17
2
2
  March 26th, 2025
3
3
  better tencent ASR
@@ -34,6 +34,7 @@ setup(
34
34
  # "pyAudioAnalysis",
35
35
  "hmmlearn==0.3.0",
36
36
  "eyed3",
37
+ "opencc-python-reimplemented",
37
38
  "pydub",
38
39
  "imblearn",
39
40
  "plotly>=5.3.0",