* Add Silero VAD model and integrate it into the transcription filter
* Fix Silero VAD model path and enable n_threads
* Update translation strings for multiple locales
* Update Onnxruntime library linking and fix compiler warning
* Fix variable naming and type casting in Silero VAD implementation
* Update Silero VAD model path and enable n_threads
* Enable CoreML and allow fallback to CPU on MacOS ARM64
* Disable CoreML support on MacOS ARM64
* Fix build configuration for MacOS
* Update macOS build configuration based on MACOS_ARCH environment variable
* Update BuildWhispercpp.cmake to disable FMA instructions on non-Apple platforms
* Add cuBLAS support to build and package actions
* Update Cublas versions in Windows build and packaging scripts
* Update CUDA_TOOLKIT_ROOT_DIR environment variable
* Add sub-packages and non-cuda-sub-packages options to CUDA toolkit setup
* Update CUDA sub-packages in build-project.yaml
* Add "visual_studio_integration" to sub-packages in CUDA build workflow
* Fix typo in build-project.yaml
* Fix typo in CUDA build method
* Update sub-packages in CUDA toolkit installation
* Remove unnecessary CUDA sub-packages and method
* Update buffer size and overlap size handling
* Refactor buffer size calculation and formatting in transcription filter
This commit refactors the buffer size calculation in the transcription filter code to improve readability and maintainability. The code now uses a more concise and formatted approach to calculate the buffer size in milliseconds. Additionally, the commit also improves the formatting and readability of the code in the whisper-processing file. These changes enhance the overall code quality and maintainability.
* Update save_srt option and add truncate_output_file option
* Refactor code for readability and maintainability
* Update clang-format version to 16.0.5
* Update .clang-format and model-downloader-ui.cpp
* Fix is_lead_byte and is_trail_byte macros
