batchalign 0.7.17.post2__tar.gz → 0.7.17.post4__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. {batchalign-0.7.17.post2/batchalign.egg-info → batchalign-0.7.17.post4}/PKG-INFO +10 -2
  2. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/whisper/infer_asr.py +23 -11
  3. batchalign-0.7.17.post4/batchalign/version +3 -0
  4. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4/batchalign.egg-info}/PKG-INFO +10 -2
  5. batchalign-0.7.17.post2/batchalign/version +0 -3
  6. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/LICENSE +0 -0
  7. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/MANIFEST.in +0 -0
  8. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/README.md +0 -0
  9. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/__init__.py +0 -0
  10. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/__main__.py +0 -0
  11. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/cli/__init__.py +0 -0
  12. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/cli/cli.py +0 -0
  13. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/cli/dispatch.py +0 -0
  14. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/constants.py +0 -0
  15. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/document.py +0 -0
  16. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/errors.py +0 -0
  17. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/__init__.py +0 -0
  18. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/base.py +0 -0
  19. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/chat/__init__.py +0 -0
  20. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/chat/file.py +0 -0
  21. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/chat/generator.py +0 -0
  22. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/chat/lexer.py +0 -0
  23. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/chat/parser.py +0 -0
  24. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/chat/utils.py +0 -0
  25. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/textgrid/__init__.py +0 -0
  26. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/textgrid/file.py +0 -0
  27. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/textgrid/generator.py +0 -0
  28. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/formats/textgrid/parser.py +0 -0
  29. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/__init__.py +0 -0
  30. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/resolve.py +0 -0
  31. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/speaker/__init__.py +0 -0
  32. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/speaker/config.yaml +0 -0
  33. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/speaker/infer.py +0 -0
  34. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/speaker/utils.py +0 -0
  35. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/training/__init__.py +0 -0
  36. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/training/run.py +0 -0
  37. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/training/utils.py +0 -0
  38. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utils.py +0 -0
  39. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utterance/__init__.py +0 -0
  40. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utterance/cantonese_infer.py +0 -0
  41. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utterance/dataset.py +0 -0
  42. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utterance/execute.py +0 -0
  43. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utterance/infer.py +0 -0
  44. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utterance/prep.py +0 -0
  45. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/utterance/train.py +0 -0
  46. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/wave2vec/__init__.py +0 -0
  47. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/wave2vec/infer_fa.py +0 -0
  48. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/whisper/__init__.py +0 -0
  49. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/models/whisper/infer_fa.py +0 -0
  50. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/__init__.py +0 -0
  51. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/analysis/__init__.py +0 -0
  52. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/analysis/eval.py +0 -0
  53. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/asr/__init__.py +0 -0
  54. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/asr/num2chinese.py +0 -0
  55. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/asr/rev.py +0 -0
  56. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/asr/utils.py +0 -0
  57. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/asr/whisper.py +0 -0
  58. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/asr/whisperx.py +0 -0
  59. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/base.py +0 -0
  60. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/__init__.py +0 -0
  61. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/cleanup.py +0 -0
  62. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
  63. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/parse_support.py +0 -0
  64. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/retrace.py +0 -0
  65. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
  66. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
  67. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/cleanup/support/test.test +0 -0
  68. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/dispatch.py +0 -0
  69. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/fa/__init__.py +0 -0
  70. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/fa/wave2vec_fa.py +0 -0
  71. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/fa/whisper_fa.py +0 -0
  72. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
  73. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/coref.py +0 -0
  74. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
  75. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/fr/apm.py +0 -0
  76. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/fr/apmn.py +0 -0
  77. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
  78. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
  79. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/morphosyntax/ud.py +0 -0
  80. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/pipeline.py +0 -0
  81. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/speaker/__init__.py +0 -0
  82. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
  83. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/translate/__init__.py +0 -0
  84. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/translate/seamless.py +0 -0
  85. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/utr/__init__.py +0 -0
  86. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/utr/rev_utr.py +0 -0
  87. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/utr/utils.py +0 -0
  88. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/utr/whisper_utr.py +0 -0
  89. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/utterance/__init__.py +0 -0
  90. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
  91. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/__init__.py +0 -0
  92. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/conftest.py +0 -0
  93. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
  94. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
  95. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
  96. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
  97. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
  98. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
  99. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
  100. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
  101. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
  102. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
  103. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
  104. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
  105. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/fixures.py +0 -0
  106. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/test_pipeline.py +0 -0
  107. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
  108. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/tests/test_document.py +0 -0
  109. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/utils/__init__.py +0 -0
  110. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/utils/config.py +0 -0
  111. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/utils/dp.py +0 -0
  112. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign/utils/utils.py +0 -0
  113. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign.egg-info/SOURCES.txt +0 -0
  114. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign.egg-info/dependency_links.txt +0 -0
  115. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign.egg-info/entry_points.txt +0 -0
  116. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign.egg-info/requires.txt +0 -0
  117. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/batchalign.egg-info/top_level.txt +0 -0
  118. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/setup.cfg +0 -0
  119. {batchalign-0.7.17.post2 → batchalign-0.7.17.post4}/setup.py +0 -0
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.1
1
+ Metadata-Version: 2.2
2
2
  Name: batchalign
3
- Version: 0.7.17.post2
3
+ Version: 0.7.17.post4
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
@@ -40,6 +40,14 @@ Provides-Extra: dev
40
40
  Requires-Dist: pytest; extra == "dev"
41
41
  Provides-Extra: train
42
42
  Requires-Dist: accelerate~=0.27; extra == "train"
43
+ Dynamic: author
44
+ Dynamic: author-email
45
+ Dynamic: classifier
46
+ Dynamic: description
47
+ Dynamic: description-content-type
48
+ Dynamic: provides-extra
49
+ Dynamic: requires-dist
50
+ Dynamic: summary
43
51
 
44
52
  # TalkBank | Batchalign2
45
53
 
@@ -67,7 +67,7 @@ class WhisperASRModel(object):
67
67
  L.debug("Initializing whisper model...")
68
68
  self.__config = GenerationConfig.from_pretrained(base)
69
69
  self.__config.no_repeat_ngram_size = 4
70
-
70
+ self.__config.use_cache = True
71
71
 
72
72
  if language == "Cantonese":
73
73
  self.__config.no_repeat_ngram_size = 4
@@ -84,16 +84,28 @@ class WhisperASRModel(object):
84
84
  [10, 5]
85
85
  ]
86
86
 
87
- self.pipe = pipeline(
88
- "automatic-speech-recognition",
89
- model=model,
90
- tokenizer=WhisperTokenizer.from_pretrained(base),
91
- chunk_length_s=25,
92
- stride_length_s=3,
93
- device=DEVICE,
94
- torch_dtype=torch.float32,
95
- return_timestamps="word",
96
- )
87
+ try:
88
+ self.pipe = pipeline(
89
+ "automatic-speech-recognition",
90
+ model=model,
91
+ tokenizer=WhisperTokenizer.from_pretrained(base),
92
+ chunk_length_s=25,
93
+ stride_length_s=3,
94
+ device=DEVICE,
95
+ torch_dtype=torch.bfloat16,
96
+ return_timestamps="word",
97
+ )
98
+ except TypeError:
99
+ self.pipe = pipeline(
100
+ "automatic-speech-recognition",
101
+ model=model,
102
+ tokenizer=WhisperTokenizer.from_pretrained(base),
103
+ chunk_length_s=25,
104
+ stride_length_s=3,
105
+ device=DEVICE,
106
+ torch_dtype=torch.float16,
107
+ return_timestamps="word",
108
+ )
97
109
  L.debug("Done, initalizing processor and config...")
98
110
  processor = WhisperProcessor.from_pretrained(base)
99
111
  L.debug("Whisper initialization done.")
@@ -0,0 +1,3 @@
1
+ 0.7.17-post.4
2
+ March 8th, 2025
3
+ kvcaching for whisper
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.1
1
+ Metadata-Version: 2.2
2
2
  Name: batchalign
3
- Version: 0.7.17.post2
3
+ Version: 0.7.17.post4
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
@@ -40,6 +40,14 @@ Provides-Extra: dev
40
40
  Requires-Dist: pytest; extra == "dev"
41
41
  Provides-Extra: train
42
42
  Requires-Dist: accelerate~=0.27; extra == "train"
43
+ Dynamic: author
44
+ Dynamic: author-email
45
+ Dynamic: classifier
46
+ Dynamic: description
47
+ Dynamic: description-content-type
48
+ Dynamic: provides-extra
49
+ Dynamic: requires-dist
50
+ Dynamic: summary
43
51
 
44
52
  # TalkBank | Batchalign2
45
53
 
@@ -1,3 +0,0 @@
1
- 0.7.17-post.2
2
- March 7th, 2025
3
- revert final delimeter