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

LocalVocal: Local Live Captions & Translation On-the-Go v0.3.5

Go to download
Overview Updates (19) Reviews (8) History Discussion

v0.3.5 - Upgrades, improvements - the good stuff!

In this release:
  • Upgrade Silero VAD to v5
  • Upgrade to latest whisper.cpp
  • Filter words UI improvement
  • Improvements to real-time translation
  • Improvement to very short audio chunks
Enjoy!

Download:

v0.3.4 AMD GPU! CoreML and Metal! Accelerate!

Much rejoicing! Introducing AMD ROCm / hipBLAS acceleration, as well as CoreML and Metal on Apple!
This was tested to give tremendous performance boosts on Apple and AMD GPUs.

Also in this release:
  • bumping to the latest whisper.cpp
  • fixing the captions stream issue on Twitch and YouTube
  • fixing the translation captions disappearance.
Enjoy and let me know of any problems!

Download:
  • Like
Reactions: Tallicia and uuoocl

v0.3.3 Partial real-time Transcripts! new OBS, many bugfixes

In this release:
  • New simplified and streamlined filter UI, and properties refactoring
  • File output fixes
  • Model loading fixes
  • Language selection bug fix
  • Partial transcription option
  • More bugfixes
Download:
  • Like
Reactions: OpenFields

v0.3.2 Improvements all around! Caption presentation, logs and bugfixes

Lots of things going on in this busy release!

  • Adding filter & replace option
  • Improving buffered output a lot making it much nicer (like word wrapping, word-by-word mode)
  • Improving the translation-sentence cadence
  • Fixing logs and potential crash-causing bugs

Download​

  • Like
Reactions: uuoocl and OpenFields

v0.3.1 - more models, fix timestamps

In this release:
  • Adding more whisper model options
  • Only allowing English selection for English models
  • Freeing up resources on filter disable
  • Fixing a bug to make accurate timestamps
Download:
  • Like
Reactions: OpenFields

v0.3.0 Big release! Far better experience, more translation, bugs squashed!

Big release! Many improvements, solving a lot of bugs and introducing far better performance.
In points:
  • VAD based segmentation - no more "3 seconds segments"! when speech is detected the transcription kicks in
  • Incremental output: The captions will appear continuously as you speak, a live transcription effect
  • Bumping the version of whisper.cpp
  • Many more options for real-time translation
  • A lot of bug fixing...
Download

v0.2.6 - More robust, better translation, Linux fix

A big release. Fixing things and adding evaluation tools
  • Fixing Linux problems with missing dependency
  • Testing tools and scripts for evaluating the algorithm
  • Add Whisper-based translation
  • Add M2M100 1.2B model for translation
  • Optimizing overlap regions
  • Sentence suppression fixup
Download

v0.2.3 - BEST version yet! Fixes and performance updates

Our BEST version of LocalVocal yet!

Bumping whisper versions, fixing buffers for smooth transitions, simplifying UI, adding suppression mechanism...
It's an overhaul...

Enjoy!

  • Like
Reactions: uuoocl

v0.2.1 - Translation! Built-in!

This version adds built-in translation for live captioning.
Translating to-and-from ~100 languages, simply by clicking a button.

Enjoy!

Download:
  • Like
Reactions: OpenFields

v0.2.0 - CUDA on Windows! Mac Apple ARM optimization!

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
Top