Faster-Whisper-XXL r192.3.4

Standalone Faster-Whisper implementation using optimized CTranslate2 models.

Includes all Standalone Faster-Whisper features +some additional ones.
Includes all needed libs.
Read there ->#231

Some new stuff in r192.3.4:

New feature: Write intermediate files to temp folder. [ignored on dump]
New feature: Can take JSON files as input to generate subtitles from it according to the settings.
New alternative VAD method : pyannote_v3 [previous same named option renamed to "pyannote_onnx_v3"]
New arg: --nullify_non_speech [for WIP experiments]

Link to the changelog.

Faster-Whisper r192.3

Standalone Faster-Whisper implementation using optimized CTranslate2 models.

GPU execution requires cuBLAS and cuDNN 8.x libs for CUDA v11.x .

Last included commit: #192

Some new stuff in r192.3:

Bugfix: 'one_word' was broken in r192.2.

Link to the changelog.

Whisper-OpenAI r136

Last included commit: #136.

Notes:

Needs FFmpeg in PATH or place it in the same folder with Whisper executable.
"CPU" build runs only on CPU.

cuBLAS and cuDNN

Place libs in the same folder where Faster-Whisper executable is. Or to:
Windows: To System32 dir.
Linux: To dir in LD_LIBRARY_PATH env.

.7z vs .zip - archives contain same files.

v2 is the last with support for GPUs with Kepler chip.