v1.9.1

Fixed

• Fixed Whisperx diarization pipeline initialization
• Fixed Whisperx language detection

What's Changed

• Release 1.9.0 by @ahmetoner in #316
• Fix whisperx diarization pipeline init and language detection by @ahmetoner in #317

Full Changelog: v1.9.0...v1.9.1

v1.9.0

Discord Server

🎉 Join our Discord Community! Connect with other users, get help, and stay updated on the latest features: https://discord.gg/4Q5YVrePzZ

Changed

• Upgraded
  • Poetry to v2.1.3
  • openai/whisper@v20250625
  • SYSTRAN/faster-whisper to v1.1.1
  • whisperX@v3.4.2
  • torch to v2.7.1
  • torchaudio to v2.7.1
  • numpy to v2.2.6
  • fastapi to v0.115.14
  • uvicorn to v0.35.0
  • numba to v0.61.2

What's Changed

• Upgrade dependencies by @ahmetoner in #315

Full Changelog: v1.8.2...v1.9.0

v1.8.2

What's Changed

• Reduced GPU image size by using nvidia/cuda:12.6.3-base-ubuntu22.04 in #287

Full Changelog: v1.8.1...v1.8.2

v1.8.1

What's Changed

Fixed

• Fix issues with Torch CUDA and cuDNN, fixes #283 and #284 by @ahmetoner in #285
• Updated Torch and Torchaudio dependencies for multi-architecture support

Full Changelog: v1.8.0...v1.8.1

v1.8.0

Added

• Added support for whisperX@v3.1.1

Changed

• Upgraded Cuda GPU image to v12.6.3
• Upgraded dependencies
  • torch to v2.6.0
  • fastapi to v0.115.8
  • llvmlite to v0.44.0
  • numba to v0.61.0
  • ruff to v0.9.6
  • black to v25.1.0
  • mkdocs-material to v9.6.4
  • pymdown-extensions to v10.14.3

What's Changed

• Whisperx integration by @charnesp in #267 and #281

New Contributors

• @charnesp made their first contribution in #267

Full Changelog: v1.7.1...v1.8.0

v1.7.1

What's Changed

• Fix JSON serialization of segments due to Faster Whisper v1.1.0 changes by @ahmetoner in #265

Full Changelog: v1.7.0...v1.7.1

v1.7.0

Added

• Timeout configured to allow model to be unloaded when idle

  MODEL_IDLE_TIMEOUT=300

  Defaults to 0. After no activity for this period (in seconds), unload the model until it is requested again. Setting
  0 disables the timeout, keeping the model loaded indefinitely.

• Added detection confidence to langauge detection endpoint

• Set mel generation to adjust n_dims automatically to match the loaded model

• Refactor classes, Add comments, implement abstract methods, and add factory method for engine selection

Changed

• Upgraded
  • SYSTRAN/faster-whisper to v1.1.0
  • uvicorn to v0.34.0
  • tqdm to v4.67.1
  • python-multipart to v0.0.20
  • fastapi to v0.115.6
  • pytest to v8.3.4
  • ruff to v0.8.3
  • black to v24.10.0
  • mkdocs to v1.6.1
  • mkdocs-material to v9.5.49
  • pymdown-extensions to v10.12

What's Changed

• Correctly load n_dims for openai_whisper model by @aidancrowther in #259
• Add confidence percentage to language detection by @aidancrowther in #260
• Fix typo in Endpoints Documentation by @MatthewGlenn in #239
• Fix incorrect spelling of output param in docs by @kaveet in #243
• Add vram flushing support by @aidancrowther in #256
• Refactor classes and upgrade faster whisper to v1.1.0 by @ahmetoner in #261

New Contributors

• @aidancrowther made their first contribution in #259
• @MatthewGlenn made their first contribution in #239
• @kaveet made their first contribution in #243

Full Changelog: v1.6.0...v1.7.0

v1.6.0

Changed

• Upgraded
  • openai/whisper@v20240930
  • fastapi to v0.115.0
  • uvicorn to v0.31.0
  • tqdm to v4.66.5
  • python-multipart to v0.0.12

What's Changed

• Release 1.5.0 by @ahmetoner in #231
• Upgrade OpenAI Whisper to v20240930 (turbo) by @ahmetoner in #244

Full Changelog: v1.5.0...v1.6.0

v1.5.0

Changed

• Upgraded
  • SYSTRAN/faster-whisper to v1.0.3
  • fastapi to v0.111.0
  • uvicorn to v0.30.1
  • gunicorn to v22.0.0
  • tqdm to v4.66.4
  • llvmlite to v0.43.0
  • numba to v0.60.0

Full Changelog: v1.4.1...v1.5.0

v1.4.1

Changed

• Upgraded torch to v1.13.1

What's Changed

• Upgrade torch to v1.13.1, fixes #206 by @ahmetoner in #212

Full Changelog: v1.4.0...v1.4.1