Skip to content

Releases: sensein/senselab

1.3.1-alpha.34

1.3.1-alpha.34 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 22 Jul 20:02
ec5c98b

🐛 Bug Fix

  • feat(canary): split long audio at pauses to avoid the ~40s truncation #534 (@wilke0818)

Authors: 1

1.3.1-alpha.33

1.3.1-alpha.33 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 18 May 16:05
bd6b60d

🐛 Bug Fix

  • ScriptLine: accept empty text as "model produced no transcript" signal #520 (@wilke0818)

Authors: 1

1.3.1-alpha.32

1.3.1-alpha.32 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 18 May 16:03
bc78592

🐛 Bug Fix

Authors: 1

1.3.1-alpha.31

1.3.1-alpha.31 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 15 May 16:04
183529a

🐛 Bug Fix

  • subprocess_venv: route torch/torchaudio via CUDA-aware PyTorch index #516 (@satra @wilke0818)
  • subprocess_venv: two-stage install to fix torch/torchaudio CUDA-tag s… #518 (@wilke0818)

Authors: 2

1.3.1-alpha.30

1.3.1-alpha.30 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 13 May 00:44
1443cdf

🐛 Bug Fix

Authors: 3

1.3.1-alpha.29

1.3.1-alpha.29 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 10 May 22:53
bcf612c

🐛 Bug Fix

  • comparison & uncertainty stage for analyze_audio.py #512 (@satra)

Authors: 1

1.3.1-alpha.28

1.3.1-alpha.28 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 08 May 21:30
71a2a85

🐛 Bug Fix

  • audio analysis script + multilingual MMS aligner + 4 new ASR backends #510 (@satra)

⚠️ Pushed to alpha

  • Shell-quote report path in 'Open with' hint (@satra)

Authors: 1

1.3.1-alpha.27

1.3.1-alpha.27 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 05 May 03:52
1a2955a

🐛 Bug Fix

  • Add scalene profiling wrapper as opt-in dependency group #507 (@satra)

⚠️ Pushed to alpha

  • Add venv_python() helper for cross-platform venv Python path (@satra)
  • Remove redundant bounds check in YAMNet timestamp loop (@satra)

Authors: 1

1.3.1-alpha.26

1.3.1-alpha.26 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 01 May 14:20
865d626

🐛 Bug Fix

  • Add YAMNet subprocess backend and auto-resampling for classification #505 (@satra)

Authors: 1

1.3.1-alpha.25

1.3.1-alpha.25 Pre-release
Pre-release

Choose a tag to compare

@satra satra released this 30 Apr 19:37
4cc35bd

Changes since 1.3.1-alpha.24

  • Windowed auditory scene classification (classify_audios(..., win_length=))
  • PPG venv fix (removed unnecessary espnet/snorkel/lightning deps)
  • NeMo venv: added pyarrow<18 + matplotlib
  • Pipeline cache key fix (model+device only)
  • Removed stale top_k workaround (HF bug fixed upstream)
  • Classification docs naming fix