LocalVocal: Local Live Captions & Translation On-the-Go

LocalVocal: Local Live Captions & Translation On-the-Go v0.2.1

Introducing: CUDA for Windows!
Now compiling Whisper.cpp vs. CUDA 11 and 12 for GPU accelerated runtime on Windows, which can result in ~x5-x10 faster inference.
With GPU acceleration you can now go for bigger models like Medium and still have very fast transcription with incredible accuracy in many languages.

Also introducing MacOS Apple Silicon optimizations for M1/M2/M3 processors, which results in performance bumps and utilizes your hardware better.

Enjoy!

Download:
  • Like
Reactions: BenAndo

What's Changed​

  • Update Whisper.cpp version by @royshil in #72
  • Variable buffer size options by @royshil in #66
  • Fix Max Channels, Update macOS brew command and fix compiler warnings by @royshil in #75
Download
  • Like
Reactions: OpenFields
In this release:

  • Bump Whisper.cpp - more CPU performance gains (~5-10% improvement)
  • Adding an option to not truncate the output text file
Download:
In this release:
  • Bump Whisper.cpp for another ~10% gains in speed / processing
  • Add "Simple Mode" for settings so people don't run away screaming :D
  • Internal shuffling that results in a more robust plugin, less crashy
Enjoy!

Download links:
  • Like
Reactions: OpenFields
This release bumps Whisper.cpp to a version that brings ~25% gains in performance (!), and also fixing the notorious "remove filter crash" bug.
Let me know if you experience any issues!

If you'd like to support my work consider Patreon or GitHub Sponsors, a ⭐ on the repo would be greatly appreciated and a rating on the OBS forum

What's Changed​

Full Changelog: 0.0.6...0.0.7
In this release: Minimum subtitle display duration, removing the vexing [skip] message, fixing ALL unicode languages as well as Windows UTF8 paths for custom model files

If this plugin has provided value to you consider adding a ⭐ on the repo, subscribing to my YouTube channel where I post updates, and supporting my work: https://github.com/sponsors/royshil

What's Changed​

  • Adding min sub render duration by @royshil in #46
  • Fix windows Unicode model path and characters display by @royshil in #47
Full Changelog: 0.0.5...0.0.6
In this release I'm fixing an important bug with UTF8 characters not being handled properly on Windows. Also an change that allows for far faster builds.

If this plugin has provided value to you consider adding a ⭐ on the repo, subscribing to my YouTube channel where I post updates, and supporting my work: https://github.com/sponsors/royshil

Installers:
A very exciting release! We have improvements and new features all around:
  • Saving subtitles to .srt files
  • Saving subtitles aligned to OBS recordings (timestamp, filename)
  • Using external Whisper models
  • CUDA support for Windows
  • Disable on audio source mute
  • Fixing UTF8 characters for certain languages
  • Translation of the UI
If this plugin has provided value to you consider adding a ⭐ on the repo, subscribing to my YouTube channel where I post updates, and supporting my work: https://github.com/sponsors/royshil

What's Changed​

Full Changelog: 0.0.3...0.0.4
  • Like
Reactions: lcalder
In this release we have several important updates: send captions to an RTMP stream, fixing the model download issues, step-by-step transcription (realtime transcription effect). New version of Whisper.cpp has major speedup on Mac CPUs!

If this plugin has provided value to you consider adding a ⭐ on the GH repo, subscribing to my YouTube channel, and supporting my work: https://github.com/sponsors/royshil

I will upload a new video soon with instructions on the new features.

What's Changed​

New Contributors​

Full Changelog: 0.0.2...0.0.3
Top