pyannote.audio 3.3.0__tar.gz → 3.3.2__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 (233) hide show
  1. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/workflows/test.yml +1 -1
  2. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/CHANGELOG.md +19 -0
  3. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/PKG-INFO +4 -4
  4. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/core/inference.py +1 -1
  5. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/core/pipeline.py +2 -1
  6. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/speaker_diarization.py +1 -2
  7. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/speaker_verification.py +6 -6
  8. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/speech_separation.py +4 -4
  9. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/segmentation/mixins.py +1 -1
  10. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/segmentation/speaker_diarization.py +1 -1
  11. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/separation/PixIT.py +1 -1
  12. pyannote_audio-3.3.2/pyannote/audio/version.py +1 -0
  13. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/PKG-INFO +4 -4
  14. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/SOURCES.txt +1 -0
  15. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/requires.txt +1 -1
  16. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/requirements.txt +1 -1
  17. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/setup.cfg +1 -1
  18. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/setup.py +1 -1
  19. pyannote_audio-3.3.2/tests/test_speechbrain.py +20 -0
  20. pyannote_audio-3.3.2/version.txt +1 -0
  21. pyannote_audio-3.3.0/pyannote/audio/version.py +0 -1
  22. pyannote_audio-3.3.0/version.txt +0 -1
  23. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.faq/FAQ.md +0 -0
  24. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.faq/suggest.md +0 -0
  25. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.gitattributes +0 -0
  26. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/FUNDING.yml +0 -0
  27. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/ISSUE_TEMPLATE/bug_report.yml +0 -0
  28. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/ISSUE_TEMPLATE/config.yml +0 -0
  29. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/stale.yml +0 -0
  30. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/workflows/doc.yml +0 -0
  31. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/workflows/pypi.yml +0 -0
  32. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.github/workflows/test_cli.yml +0 -0
  33. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.gitignore +0 -0
  34. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.gitmodules +0 -0
  35. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/.pre-commit-config.yaml +0 -0
  36. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/CODE_OF_CONDUCT.md +0 -0
  37. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/FAQ.md +0 -0
  38. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/LICENSE +0 -0
  39. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/MANIFEST.in +0 -0
  40. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/README.md +0 -0
  41. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/codecov.yml +0 -0
  42. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/doc/gen_docs.py +0 -0
  43. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/doc/requirements.txt +0 -0
  44. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/doc/source/index.rst +0 -0
  45. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/environment.yaml +0 -0
  46. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/faq.yml +0 -0
  47. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/notebook/augmentation.ipynb +0 -0
  48. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/notebook/example.ipynb +0 -0
  49. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/notebook/freeze.ipynb +0 -0
  50. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/notebook/inference.ipynb +0 -0
  51. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/notebook/sharing.ipynb +0 -0
  52. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/__init__.py +0 -0
  53. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/__init__.py +0 -0
  54. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/augmentation/__init__.py +0 -0
  55. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/augmentation/mix.py +0 -0
  56. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/augmentation/registry.py +0 -0
  57. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/__init__.py +0 -0
  58. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/config/hydra/default.yaml +0 -0
  59. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/evaluate.py +0 -0
  60. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/evaluate_config/__init__.py +0 -0
  61. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/evaluate_config/config.yaml +0 -0
  62. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/evaluate_config/hydra/default.yaml +0 -0
  63. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/lr_schedulers/CosineAnnealingWarmRestarts.py +0 -0
  64. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/lr_schedulers/CyclicLR.py +0 -0
  65. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/lr_schedulers/ReduceLROnPlateau.py +0 -0
  66. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/lr_schedulers/__init__.py +0 -0
  67. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/pretrained.py +0 -0
  68. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train.py +0 -0
  69. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/__init__.py +0 -0
  70. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/config.yaml +0 -0
  71. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/hydra/default.yaml +0 -0
  72. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/model/DebugEmbedding.yaml +0 -0
  73. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/model/DebugSegmentation.yaml +0 -0
  74. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/model/Pretrained.yaml +0 -0
  75. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/model/PyanNet.yaml +0 -0
  76. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/model/SSeRiouSS.yaml +0 -0
  77. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/model/XVectorMFCC.yaml +0 -0
  78. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/model/XVectorSincNet.yaml +0 -0
  79. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/optimizer/Adam.yaml +0 -0
  80. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/optimizer/AdamW.yaml +0 -0
  81. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/optimizer/Adan.yaml +0 -0
  82. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/preprocessor/LowerTemporalResolution.yaml +0 -0
  83. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/scheduler/CosineAnnealingWarmRestarts.yaml +0 -0
  84. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/scheduler/CyclicLR.yaml +0 -0
  85. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/scheduler/ReduceLROnPlateau.yaml +0 -0
  86. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/task/MultiLabelSegmentation.yaml +0 -0
  87. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/task/OverlappedSpeechDetection.yaml +0 -0
  88. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/task/SpeakerDiarization.yaml +0 -0
  89. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/task/SpeakerEmbedding.yaml +0 -0
  90. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/task/VoiceActivityDetection.yaml +0 -0
  91. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/trainer/default.yaml +0 -0
  92. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/cli/train_config/trainer/fast_dev_run.yaml +0 -0
  93. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/core/__init__.py +0 -0
  94. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/core/callback.py +0 -0
  95. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/core/io.py +0 -0
  96. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/core/model.py +0 -0
  97. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/core/task.py +0 -0
  98. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/__init__.py +0 -0
  99. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/blocks/pooling.py +0 -0
  100. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/blocks/sincnet.py +0 -0
  101. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/embedding/__init__.py +0 -0
  102. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/embedding/debug.py +0 -0
  103. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/embedding/wespeaker/LICENSE.WeSpeaker +0 -0
  104. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/embedding/wespeaker/__init__.py +0 -0
  105. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/embedding/wespeaker/convert.py +0 -0
  106. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/embedding/wespeaker/resnet.py +0 -0
  107. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/embedding/xvector.py +0 -0
  108. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/segmentation/PyanNet.py +0 -0
  109. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/segmentation/SSeRiouSS.py +0 -0
  110. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/segmentation/__init__.py +0 -0
  111. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/segmentation/debug.py +0 -0
  112. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/separation/ToTaToNet.py +0 -0
  113. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/models/separation/__init__.py +0 -0
  114. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/__init__.py +0 -0
  115. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/clustering.py +0 -0
  116. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/multilabel.py +0 -0
  117. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/overlapped_speech_detection.py +0 -0
  118. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/resegmentation.py +0 -0
  119. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/utils/__init__.py +0 -0
  120. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/utils/diarization.py +0 -0
  121. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/utils/getter.py +0 -0
  122. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/utils/hook.py +0 -0
  123. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/utils/oracle.py +0 -0
  124. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/pipelines/voice_activity_detection.py +0 -0
  125. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/sample/__init__.py +0 -0
  126. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/sample/sample.rttm +0 -0
  127. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/sample/sample.wav +0 -0
  128. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/__init__.py +0 -0
  129. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/embedding/__init__.py +0 -0
  130. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/embedding/arcface.py +0 -0
  131. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/embedding/mixins.py +0 -0
  132. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/segmentation/__init__.py +0 -0
  133. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/segmentation/multilabel.py +0 -0
  134. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/segmentation/overlapped_speech_detection.py +0 -0
  135. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/segmentation/voice_activity_detection.py +0 -0
  136. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/tasks/separation/__init__.py +0 -0
  137. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/__init__.py +0 -0
  138. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/audio/__init__.py +0 -0
  139. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/audio/diarization_error_rate.py +0 -0
  140. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/classification/__init__.py +0 -0
  141. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/classification/equal_error_rate.py +0 -0
  142. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/functional/__init__.py +0 -0
  143. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/functional/audio/__init__.py +0 -0
  144. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/torchmetrics/functional/audio/diarization_error_rate.py +0 -0
  145. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/__init__.py +0 -0
  146. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/loss.py +0 -0
  147. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/metric.py +0 -0
  148. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/multi_task.py +0 -0
  149. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/params.py +0 -0
  150. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/permutation.py +0 -0
  151. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/powerset.py +0 -0
  152. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/preprocessors.py +0 -0
  153. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/preview.py +0 -0
  154. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/probe.py +0 -0
  155. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/protocol.py +0 -0
  156. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/random.py +0 -0
  157. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/receptive_field.py +0 -0
  158. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/reproducibility.py +0 -0
  159. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/signal.py +0 -0
  160. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote/audio/utils/version.py +0 -0
  161. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/dependency_links.txt +0 -0
  162. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/entry_points.txt +0 -0
  163. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/namespace_packages.txt +0 -0
  164. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/not-zip-safe +0 -0
  165. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/pyannote.audio.egg-info/top_level.txt +0 -0
  166. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/questions/README.md +0 -0
  167. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/questions/bad_performance.question.md +0 -0
  168. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/questions/from_memory.question.md +0 -0
  169. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/questions/offline.question.md +0 -0
  170. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/questions/pyannote.question.md +0 -0
  171. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/questions/streaming.question.md +0 -0
  172. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/conftest.py +0 -0
  173. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/database.yml +0 -0
  174. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.development.lst +0 -0
  175. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.development.rttm +0 -0
  176. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.development.uem +0 -0
  177. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.test.lst +0 -0
  178. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.test.rttm +0 -0
  179. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.test.uem +0 -0
  180. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.train.lst +0 -0
  181. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.train.rttm +0 -0
  182. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/debug.train.uem +0 -0
  183. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/dev00.wav +0 -0
  184. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/dev01.wav +0 -0
  185. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/empty.wav +0 -0
  186. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn01.wav +0 -0
  187. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn02.wav +0 -0
  188. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn03.wav +0 -0
  189. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn04.wav +0 -0
  190. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn05.wav +0 -0
  191. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn06.wav +0 -0
  192. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn07.wav +0 -0
  193. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn08.wav +0 -0
  194. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/trn09.wav +0 -0
  195. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/tr/303/26100.wav" +0 -0
  196. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/tst00.wav +0 -0
  197. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/data/tst01.wav +0 -0
  198. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/inference_test.py +0 -0
  199. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/io_test.py +0 -0
  200. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/tasks/test_reproducibility.py +0 -0
  201. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/tasks/test_specifications.py +0 -0
  202. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_cli.py +0 -0
  203. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_clustering.py +0 -0
  204. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_import_lib.py +0 -0
  205. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_metrics.py +0 -0
  206. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_run_notebooks.py +0 -0
  207. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_sample.py +0 -0
  208. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_stats_pool.py +0 -0
  209. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/test_train.py +0 -0
  210. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/utils/preview.py +0 -0
  211. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/utils/probe_util_test.py +0 -0
  212. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/utils/test_permutation.py +0 -0
  213. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tests/utils/test_powerset.py +0 -0
  214. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/MRE_template.ipynb +0 -0
  215. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/adapting_pretrained_pipeline.ipynb +0 -0
  216. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/add_your_own_model.ipynb +0 -0
  217. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/add_your_own_task.ipynb +0 -0
  218. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/applying_a_model.ipynb +0 -0
  219. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/applying_a_pipeline.ipynb +0 -0
  220. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/assets/download-model.png +0 -0
  221. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/assets/download-pipeline.png +0 -0
  222. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/assets/prodigy-pyannote.audio.png +0 -0
  223. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/assets/pyannote.diff.PNG +0 -0
  224. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/assets/pyannote.review.PNG +0 -0
  225. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/assets/sample.rttm +0 -0
  226. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/assets/sample.wav +0 -0
  227. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/community/offline_usage_speaker_diarization.ipynb +0 -0
  228. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/intro.ipynb +0 -0
  229. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/overlapped_speech_detection.ipynb +0 -0
  230. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/speaker_verification.ipynb +0 -0
  231. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/training_a_model.ipynb +0 -0
  232. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/training_with_cli.md +0 -0
  233. {pyannote_audio-3.3.0 → pyannote_audio-3.3.2}/tutorials/voice_activity_detection.ipynb +0 -0
@@ -13,7 +13,7 @@ jobs:
13
13
  strategy:
14
14
  matrix:
15
15
  os: [ubuntu-latest]
16
- python-version: [3.8, 3.9, "3.10"]
16
+ python-version: ["3.9", "3.10", "3.11"]
17
17
  steps:
18
18
  - uses: actions/checkout@v2
19
19
  - name: Set up Python ${{ matrix.python-version }}
@@ -1,5 +1,24 @@
1
1
  # Changelog
2
2
 
3
+ ## Version 3.3.2 (2024-09-11)
4
+
5
+ ### Fixes
6
+
7
+ - fix: (really) fix support for `numpy==2.x` ([@metal3d](https://github.com/metal3d/))
8
+ - doc: fix `Pipeline` docstring ([@huisman](https://github.com/huisman/))
9
+
10
+ ## Version 3.3.1 (2024-06-19)
11
+
12
+ ### Breaking changes
13
+
14
+ - setup: drop support for Python 3.8
15
+
16
+ ### Fixes
17
+
18
+ - fix: fix support for `numpy==2.x` ([@ibevers](https://github.com/ibevers/))
19
+ - fix: fix support for `speechbrain==1.x` ([@Adel-Moumen](https://github.com/Adel-Moumen/))
20
+
21
+
3
22
  ## Version 3.3.0 (2024-06-14)
4
23
 
5
24
  ### TL;DR
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: pyannote.audio
3
- Version: 3.3.0
3
+ Version: 3.3.2
4
4
  Summary: Neural building blocks for speaker diarization
5
5
  Home-page: https://github.com/pyannote/pyannote-audio
6
6
  Author: Hervé Bredin
@@ -12,11 +12,11 @@ Classifier: Development Status :: 4 - Beta
12
12
  Classifier: Intended Audience :: Science/Research
13
13
  Classifier: License :: OSI Approved :: MIT License
14
14
  Classifier: Natural Language :: English
15
- Classifier: Programming Language :: Python :: 3.8
16
15
  Classifier: Programming Language :: Python :: 3.9
17
16
  Classifier: Programming Language :: Python :: 3.10
17
+ Classifier: Programming Language :: Python :: 3.11
18
18
  Classifier: Topic :: Scientific/Engineering
19
- Requires-Python: >=3.7
19
+ Requires-Python: >=3.9
20
20
  Description-Content-Type: text/markdown
21
21
  License-File: LICENSE
22
22
  Requires-Dist: asteroid-filterbanks>=0.4
@@ -32,7 +32,7 @@ Requires-Dist: pytorch_metric_learning>=2.1.0
32
32
  Requires-Dist: rich>=12.0.0
33
33
  Requires-Dist: semver>=3.0.0
34
34
  Requires-Dist: soundfile>=0.12.1
35
- Requires-Dist: speechbrain>=0.5.14
35
+ Requires-Dist: speechbrain>=1.0.0
36
36
  Requires-Dist: tensorboardX>=2.6
37
37
  Requires-Dist: torch>=2.0.0
38
38
  Requires-Dist: torch_audiomentations>=0.11.0
@@ -526,7 +526,7 @@ class Inference(BaseInference):
526
526
  warm_up: Tuple[float, float] = (0.0, 0.0),
527
527
  epsilon: float = 1e-12,
528
528
  hamming: bool = False,
529
- missing: float = np.NaN,
529
+ missing: float = np.nan,
530
530
  skip_average: bool = False,
531
531
  ) -> SlidingWindowFeature:
532
532
  """Aggregation
@@ -69,7 +69,8 @@ class Pipeline(_Pipeline):
69
69
  to True or to a string containing your hugginface.co authentication
70
70
  token that can be obtained by running `huggingface-cli login`
71
71
  cache_dir: Path or str, optional
72
- Path to model cache directory. Defauorch/pyannote" when unset.
72
+ Path to model cache directory. Defaults to content of PYANNOTE_CACHE
73
+ environment variable, or "~/.cache/torch/pyannote" when unset.
73
74
  """
74
75
 
75
76
  checkpoint_path = str(checkpoint_path)
@@ -400,7 +400,7 @@ class SpeakerDiarization(SpeakerDiarizationMixin, Pipeline):
400
400
  num_chunks, num_frames, local_num_speakers = segmentations.data.shape
401
401
 
402
402
  num_clusters = np.max(hard_clusters) + 1
403
- clustered_segmentations = np.NAN * np.zeros(
403
+ clustered_segmentations = np.nan * np.zeros(
404
404
  (num_chunks, num_frames, num_clusters)
405
405
  )
406
406
 
@@ -515,7 +515,6 @@ class SpeakerDiarization(SpeakerDiarizationMixin, Pipeline):
515
515
  centroids = None
516
516
 
517
517
  else:
518
-
519
518
  # skip speaker embedding extraction with oracle clustering
520
519
  if self.klustering == "OracleClustering" and not return_embeddings:
521
520
  embeddings = None
@@ -40,7 +40,7 @@ from pyannote.audio.core.model import CACHE_DIR
40
40
  from pyannote.audio.pipelines.utils import PipelineModel, get_model
41
41
 
42
42
  try:
43
- from speechbrain.pretrained import (
43
+ from speechbrain.inference import (
44
44
  EncoderClassifier as SpeechBrain_EncoderClassifier,
45
45
  )
46
46
 
@@ -186,7 +186,7 @@ class NeMoPretrainedSpeakerEmbedding(BaseInference):
186
186
 
187
187
  # corner case: every signal is too short
188
188
  if max_len < self.min_num_samples:
189
- return np.NAN * np.zeros((batch_size, self.dimension))
189
+ return np.nan * np.zeros((batch_size, self.dimension))
190
190
 
191
191
  too_short = wav_lens < self.min_num_samples
192
192
  wav_lens[too_short] = max_len
@@ -197,7 +197,7 @@ class NeMoPretrainedSpeakerEmbedding(BaseInference):
197
197
  )
198
198
 
199
199
  embeddings = embeddings.cpu().numpy()
200
- embeddings[too_short.cpu().numpy()] = np.NAN
200
+ embeddings[too_short.cpu().numpy()] = np.nan
201
201
 
202
202
  return embeddings
203
203
 
@@ -364,7 +364,7 @@ class SpeechBrainPretrainedSpeakerEmbedding(BaseInference):
364
364
 
365
365
  # corner case: every signal is too short
366
366
  if max_len < self.min_num_samples:
367
- return np.NAN * np.zeros((batch_size, self.dimension))
367
+ return np.nan * np.zeros((batch_size, self.dimension))
368
368
 
369
369
  too_short = wav_lens < self.min_num_samples
370
370
  wav_lens = wav_lens / max_len
@@ -377,7 +377,7 @@ class SpeechBrainPretrainedSpeakerEmbedding(BaseInference):
377
377
  .numpy()
378
378
  )
379
379
 
380
- embeddings[too_short.cpu().numpy()] = np.NAN
380
+ embeddings[too_short.cpu().numpy()] = np.nan
381
381
 
382
382
  return embeddings
383
383
 
@@ -594,7 +594,7 @@ class ONNXWeSpeakerPretrainedSpeakerEmbedding(BaseInference):
594
594
 
595
595
  imasks = imasks > 0.5
596
596
 
597
- embeddings = np.NAN * np.zeros((batch_size, self.dimension))
597
+ embeddings = np.nan * np.zeros((batch_size, self.dimension))
598
598
 
599
599
  for f, (feature, imask) in enumerate(zip(features, imasks)):
600
600
  masked_feature = feature[imask]
@@ -419,7 +419,7 @@ class SpeechSeparation(SpeakerDiarizationMixin, Pipeline):
419
419
  num_chunks, num_frames, local_num_speakers = segmentations.data.shape
420
420
 
421
421
  num_clusters = np.max(hard_clusters) + 1
422
- clustered_segmentations = np.NAN * np.zeros(
422
+ clustered_segmentations = np.nan * np.zeros(
423
423
  (num_chunks, num_frames, num_clusters)
424
424
  )
425
425
 
@@ -644,9 +644,9 @@ class SpeechSeparation(SpeakerDiarizationMixin, Pipeline):
644
644
  len(speaker_activation), dtype=float
645
645
  )
646
646
 
647
- speaker_activation_with_context[
648
- np.concatenate(remaining_zeros)
649
- ] = 0.0
647
+ speaker_activation_with_context[np.concatenate(remaining_zeros)] = (
648
+ 0.0
649
+ )
650
650
 
651
651
  discrete_diarization.data.T[i] = speaker_activation_with_context
652
652
  num_sources = sources.data.shape[1]
@@ -401,7 +401,7 @@ class SegmentationTask(Task):
401
401
  )
402
402
 
403
403
  # reshape target so that there is one line per class when plotting it
404
- y[y == 0] = np.NaN
404
+ y[y == 0] = np.nan
405
405
  if len(y.shape) == 2:
406
406
  y = y[:, :, np.newaxis]
407
407
  y *= np.arange(y.shape[2])
@@ -818,7 +818,7 @@ class SpeakerDiarization(SegmentationTask):
818
818
  )
819
819
 
820
820
  # reshape target so that there is one line per class when plotting it
821
- y[y == 0] = np.NaN
821
+ y[y == 0] = np.nan
822
822
  if len(y.shape) == 2:
823
823
  y = y[:, :, np.newaxis]
824
824
  y *= np.arange(y.shape[2])
@@ -1136,7 +1136,7 @@ class PixIT(SegmentationTask):
1136
1136
  )
1137
1137
 
1138
1138
  # reshape target so that there is one line per class when plotting it
1139
- y[y == 0] = np.NaN
1139
+ y[y == 0] = np.nan
1140
1140
  if len(y.shape) == 2:
1141
1141
  y = y[:, :, np.newaxis]
1142
1142
  y *= np.arange(y.shape[2])
@@ -0,0 +1 @@
1
+ __version__ = '3.3.2'
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: pyannote.audio
3
- Version: 3.3.0
3
+ Version: 3.3.2
4
4
  Summary: Neural building blocks for speaker diarization
5
5
  Home-page: https://github.com/pyannote/pyannote-audio
6
6
  Author: Hervé Bredin
@@ -12,11 +12,11 @@ Classifier: Development Status :: 4 - Beta
12
12
  Classifier: Intended Audience :: Science/Research
13
13
  Classifier: License :: OSI Approved :: MIT License
14
14
  Classifier: Natural Language :: English
15
- Classifier: Programming Language :: Python :: 3.8
16
15
  Classifier: Programming Language :: Python :: 3.9
17
16
  Classifier: Programming Language :: Python :: 3.10
17
+ Classifier: Programming Language :: Python :: 3.11
18
18
  Classifier: Topic :: Scientific/Engineering
19
- Requires-Python: >=3.7
19
+ Requires-Python: >=3.9
20
20
  Description-Content-Type: text/markdown
21
21
  License-File: LICENSE
22
22
  Requires-Dist: asteroid-filterbanks>=0.4
@@ -32,7 +32,7 @@ Requires-Dist: pytorch_metric_learning>=2.1.0
32
32
  Requires-Dist: rich>=12.0.0
33
33
  Requires-Dist: semver>=3.0.0
34
34
  Requires-Dist: soundfile>=0.12.1
35
- Requires-Dist: speechbrain>=0.5.14
35
+ Requires-Dist: speechbrain>=1.0.0
36
36
  Requires-Dist: tensorboardX>=2.6
37
37
  Requires-Dist: torch>=2.0.0
38
38
  Requires-Dist: torch_audiomentations>=0.11.0
@@ -174,6 +174,7 @@ tests/test_import_lib.py
174
174
  tests/test_metrics.py
175
175
  tests/test_run_notebooks.py
176
176
  tests/test_sample.py
177
+ tests/test_speechbrain.py
177
178
  tests/test_stats_pool.py
178
179
  tests/test_train.py
179
180
  tests/data/database.yml
@@ -11,7 +11,7 @@ pytorch_metric_learning>=2.1.0
11
11
  rich>=12.0.0
12
12
  semver>=3.0.0
13
13
  soundfile>=0.12.1
14
- speechbrain>=0.5.14
14
+ speechbrain>=1.0.0
15
15
  tensorboardX>=2.6
16
16
  torch>=2.0.0
17
17
  torch_audiomentations>=0.11.0
@@ -11,7 +11,7 @@ pytorch_metric_learning >= 2.1.0
11
11
  rich >= 12.0.0
12
12
  semver >= 3.0.0
13
13
  soundfile >= 0.12.1
14
- speechbrain >= 0.5.14
14
+ speechbrain >= 1.0.0
15
15
  tensorboardX >= 2.6
16
16
  torch >= 2.0.0
17
17
  torch_audiomentations >= 0.11.0
@@ -16,7 +16,7 @@ zip_safe = False
16
16
  packages = find:
17
17
  include_package_data = True
18
18
  setup_requires = pyscaffold>=3.2a0,<3.3a0
19
- python_requires = >=3.7
19
+ python_requires = >=3.9
20
20
 
21
21
  [options.packages.find]
22
22
  where = .
@@ -56,9 +56,9 @@ if __name__ == "__main__":
56
56
  "Intended Audience :: Science/Research",
57
57
  "License :: OSI Approved :: MIT License",
58
58
  "Natural Language :: English",
59
- "Programming Language :: Python :: 3.8",
60
59
  "Programming Language :: Python :: 3.9",
61
60
  "Programming Language :: Python :: 3.10",
61
+ "Programming Language :: Python :: 3.11",
62
62
  "Topic :: Scientific/Engineering",
63
63
  ],
64
64
  )
@@ -0,0 +1,20 @@
1
+ import tempfile
2
+ import pytest
3
+ from speechbrain.inference import EncoderClassifier
4
+
5
+
6
+ @pytest.fixture()
7
+ def cache():
8
+ return tempfile.mkdtemp()
9
+
10
+ def test_import_speechbrain_encoder_classifier(cache):
11
+ """This is a simple test that check if speechbrain
12
+ EncoderClassifier can be imported. It does not check
13
+ if the model is working properly.
14
+ """
15
+
16
+ model = EncoderClassifier.from_hparams(
17
+ source="speechbrain/spkrec-ecapa-voxceleb",
18
+ savedir=cache,
19
+ )
20
+ assert isinstance(model, EncoderClassifier)
@@ -0,0 +1 @@
1
+ 3.3.2
@@ -1 +0,0 @@
1
- __version__ = '3.3.0'
@@ -1 +0,0 @@
1
- 3.3.0
File without changes
File without changes
File without changes
File without changes