batchalign 0.7.6a31__tar.gz → 0.7.6a32__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 (112) hide show
  1. {batchalign-0.7.6a31/batchalign.egg-info → batchalign-0.7.6a32}/PKG-INFO +1 -1
  2. batchalign-0.7.6a32/batchalign/pipelines/morphosyntax/fr/apm.py +15 -0
  3. batchalign-0.7.6a32/batchalign/pipelines/morphosyntax/fr/apmn.py +81 -0
  4. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/morphosyntax/ud.py +7 -1
  5. batchalign-0.7.6a32/batchalign/version +3 -0
  6. {batchalign-0.7.6a31 → batchalign-0.7.6a32/batchalign.egg-info}/PKG-INFO +1 -1
  7. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign.egg-info/SOURCES.txt +2 -0
  8. batchalign-0.7.6a31/batchalign/version +0 -3
  9. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/LICENSE +0 -0
  10. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/MANIFEST.in +0 -0
  11. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/README.md +0 -0
  12. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/__init__.py +0 -0
  13. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/__main__.py +0 -0
  14. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/cli/__init__.py +0 -0
  15. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/cli/cli.py +0 -0
  16. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/cli/dispatch.py +0 -0
  17. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/constants.py +0 -0
  18. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/document.py +0 -0
  19. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/errors.py +0 -0
  20. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/__init__.py +0 -0
  21. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/base.py +0 -0
  22. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/chat/__init__.py +0 -0
  23. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/chat/file.py +0 -0
  24. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/chat/generator.py +0 -0
  25. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/chat/lexer.py +0 -0
  26. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/chat/parser.py +0 -0
  27. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/chat/utils.py +0 -0
  28. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/textgrid/__init__.py +0 -0
  29. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/textgrid/file.py +0 -0
  30. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/textgrid/generator.py +0 -0
  31. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/formats/textgrid/parser.py +0 -0
  32. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/__init__.py +0 -0
  33. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/resolve.py +0 -0
  34. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/speaker/__init__.py +0 -0
  35. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/speaker/config.yaml +0 -0
  36. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/speaker/infer.py +0 -0
  37. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/speaker/utils.py +0 -0
  38. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/training/__init__.py +0 -0
  39. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/training/run.py +0 -0
  40. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/training/utils.py +0 -0
  41. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/utils.py +0 -0
  42. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/utterance/__init__.py +0 -0
  43. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/utterance/dataset.py +0 -0
  44. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/utterance/execute.py +0 -0
  45. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/utterance/infer.py +0 -0
  46. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/utterance/prep.py +0 -0
  47. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/utterance/train.py +0 -0
  48. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/whisper/__init__.py +0 -0
  49. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/whisper/infer_asr.py +0 -0
  50. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/models/whisper/infer_fa.py +0 -0
  51. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/__init__.py +0 -0
  52. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/analysis/__init__.py +0 -0
  53. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/analysis/eval.py +0 -0
  54. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/asr/__init__.py +0 -0
  55. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/asr/rev.py +0 -0
  56. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/asr/utils.py +0 -0
  57. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/asr/whisper.py +0 -0
  58. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/asr/whisperx.py +0 -0
  59. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/base.py +0 -0
  60. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/__init__.py +0 -0
  61. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/cleanup.py +0 -0
  62. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
  63. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/parse_support.py +0 -0
  64. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/retrace.py +0 -0
  65. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
  66. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
  67. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/cleanup/support/test.test +0 -0
  68. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/dispatch.py +0 -0
  69. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/fa/__init__.py +0 -0
  70. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/fa/whisper_fa.py +0 -0
  71. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
  72. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/morphosyntax/coref.py +0 -0
  73. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
  74. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
  75. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
  76. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/pipeline.py +0 -0
  77. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/speaker/__init__.py +0 -0
  78. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
  79. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/utr/__init__.py +0 -0
  80. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/utr/rev_utr.py +0 -0
  81. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/utr/utils.py +0 -0
  82. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/utr/whisper_utr.py +0 -0
  83. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/utterance/__init__.py +0 -0
  84. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
  85. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/__init__.py +0 -0
  86. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/conftest.py +0 -0
  87. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
  88. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
  89. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
  90. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
  91. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
  92. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
  93. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
  94. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
  95. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
  96. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
  97. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
  98. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
  99. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/fixures.py +0 -0
  100. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/test_pipeline.py +0 -0
  101. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
  102. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/tests/test_document.py +0 -0
  103. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/utils/__init__.py +0 -0
  104. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/utils/config.py +0 -0
  105. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/utils/dp.py +0 -0
  106. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign/utils/utils.py +0 -0
  107. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign.egg-info/dependency_links.txt +0 -0
  108. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign.egg-info/entry_points.txt +0 -0
  109. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign.egg-info/requires.txt +0 -0
  110. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/batchalign.egg-info/top_level.txt +0 -0
  111. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/setup.cfg +0 -0
  112. {batchalign-0.7.6a31 → batchalign-0.7.6a32}/setup.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: batchalign
3
- Version: 0.7.6a31
3
+ Version: 0.7.6a32
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
@@ -0,0 +1,15 @@
1
+ """
2
+ auditory plural marking for french
3
+ """
4
+
5
+ from .apmn import APMN
6
+
7
+ apmn_lits = [
8
+ j.strip()
9
+ for i in APMN.strip().split("\n") if i.strip() != ""
10
+ for j in i.strip().split("\t") if j.strip() != ""
11
+ ]
12
+
13
+ def is_apm_noun(n):
14
+ return bool(n.strip().lower() in apmn_lits)
15
+
@@ -0,0 +1,81 @@
1
+ APMN = """
2
+ amiral amiraux
3
+ animal animaux
4
+ annal annaux
5
+ anormal anormaux
6
+ anticlérical anticléricaux
7
+ arsenal arsenaux
8
+ bocal bocaux
9
+ canal canaux
10
+ cantal cantaux
11
+ capital capitaux
12
+ caporal caporaux
13
+ cardinal cardinaux
14
+ central centraux
15
+ chenal chenaux
16
+ cheval chevaux
17
+ clérical cléricaux
18
+ collatéral collatéraux
19
+ colonial coloniaux
20
+ commensal commensaux
21
+ communal communaux
22
+ confessionnal confessionnaux
23
+ cordial cordiaux
24
+ corporal corporaux
25
+ cristal cristaux
26
+ cérébral cérébraux
27
+ fanal fanaux
28
+ frontal frontaux
29
+ fédéral fédéraux
30
+ féodal féodaux
31
+ gardénal gardénaux
32
+ général généraux
33
+ hôpital hôpitaux
34
+ idéal idéaux
35
+ international internationaux
36
+ journal journaux
37
+ libéral libéraux
38
+ local locaux
39
+ madrigal madrigaux
40
+ marsupial marsupiaux
41
+ maréchal maréchaux
42
+ mal maux
43
+ minéral minéraux
44
+ moral moraux
45
+ méridional méridionaux
46
+ métal métaux
47
+ nasal nasaux
48
+ national nationaux
49
+ normal normaux
50
+ numéral numéraux
51
+ occidental occidentaux
52
+ occipital occipitaux
53
+ oral oraux
54
+ ordinal ordinaux
55
+ oriental orientaux
56
+ original originaux
57
+ piédestal piédestaux
58
+ principal principaux
59
+ provincial provinciaux
60
+ quintal quintaux
61
+ radical radicaux
62
+ rival rivaux
63
+ rural ruraux
64
+ régional régionaux
65
+ sentimental sentimentaux
66
+ signal signaux
67
+ social sociaux
68
+ sénéchal sénéchaux
69
+ temporal temporaux
70
+ tergal tergaux
71
+ total totaux
72
+ tribunal tribunaux
73
+ urinal urinaux
74
+ vassal vassaux
75
+ val vaux
76
+ végétal végétaux
77
+ véronal véronals
78
+ éditorial éditoriaux
79
+ égal égaux
80
+ étal étau
81
+ """
@@ -216,6 +216,12 @@ def handler__NOUN(word, lang=None):
216
216
  case = feats.get("Case", "").replace(",", "")
217
217
  type = feats.get("PronType", "")
218
218
 
219
+ apm = ""
220
+ if lang == "fr":
221
+ from batchalign.pipelines.morphosyntax.fr.apm import is_apm_noun
222
+ apm = "apm" if is_apm_noun(word.text) else ""
223
+
224
+
219
225
  if word.deprel == "obj" and case.strip() == "":
220
226
  case = "Acc"
221
227
 
@@ -227,7 +233,7 @@ def handler__NOUN(word, lang=None):
227
233
  if gender_str == "-Com,Neut" or gender_str == "-Com" or gender_str == "-ComNeut": gender_str=""
228
234
  if number_str == "-Sing": number_str=""
229
235
 
230
- return handler(word, lang)+gender_str+number_str+stringify_feats(case, type)+ger
236
+ return handler(word, lang)+gender_str+number_str+stringify_feats(case, type)+ger+stringify_feats(apm)
231
237
 
232
238
  def handler__PROPN(word, lang=None):
233
239
  # code as noun
@@ -0,0 +1,3 @@
1
+ 0.7.6-alpha.32
2
+ November 26, 2024
3
+ French APM
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: batchalign
3
- Version: 0.7.6a31
3
+ Version: 0.7.6a32
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
@@ -73,6 +73,8 @@ batchalign/pipelines/morphosyntax/__init__.py
73
73
  batchalign/pipelines/morphosyntax/coref.py
74
74
  batchalign/pipelines/morphosyntax/ud.py
75
75
  batchalign/pipelines/morphosyntax/en/irr.py
76
+ batchalign/pipelines/morphosyntax/fr/apm.py
77
+ batchalign/pipelines/morphosyntax/fr/apmn.py
76
78
  batchalign/pipelines/morphosyntax/fr/case.py
77
79
  batchalign/pipelines/morphosyntax/ja/verbforms.py
78
80
  batchalign/pipelines/speaker/__init__.py
@@ -1,3 +0,0 @@
1
- 0.7.6-alpha.31
2
- November 22, 2024
3
- better warning message
File without changes
File without changes
File without changes
File without changes
File without changes