eXpl0it3r/WhisperSFML
1
0
Fork 0
mirror of https://github.com/eXpl0it3r/WhisperSFML.git synced 2026-01-01 10:52:59 +00:00
Code Activity
Using OpenAI's Whisper via whisper.cpp with SFML
9 commits 4 branches 0 tags 2.1 MiB
Find a file
Exact
Lukas Dürrenberger aa3916f113 Update links and year
2025-12-02 17:34:44 +01:00
.github/workflows Update GitHub Actions images 2025-12-02 15:06:23 +01:00
res Add basic whisper transcription 2023-01-24 00:56:12 +01:00
src Replace deprecated Whisper API calls 2025-12-02 15:20:57 +01:00
.gitignore Initial commit 2023-01-23 18:46:24 +01:00
CMakeLists.txt Update GitHub Actions images 2025-12-02 15:06:23 +01:00
LICENSE.md Update links and year 2025-12-02 17:34:44 +01:00
README.md Update links and year 2025-12-02 17:34:44 +01:00

README.md

WhisperSFML

Like the name WhisperSFML combines the OpenAI Whisper via Whisper.cpp and SFML to demonstrate real-time audio transcription (Speak-To-Text) as well as translation.

How To Use

  • Get the WhisperSFML source code
  • Make sure CMake and a compiler is installed
  • Get one of model files in the ggml format
    • I recommend at least base or small
  • (optional) Pick some sound file of your desire
  • Replace the filenames in the source files
  • Build and run
    • I recommend to run it in release mode

Screenshot of WhisperSFML in action

Resources

License

The code itself is is available under 2 licenses: Public Domain or MIT -- choose whichever you prefer, see also the license file.