Faster-Whisper-XXL r193.1

Standalone Faster-Whisper implementation using optimized CTranslate2 models.

Includes all Standalone Faster-Whisper features + some additional ones. Read here.
Faster-Whisper-XXL releases include all needed libs.

Some new stuff in r193.1:

New feature: Diarization.
New feature: large-v3-turbo model autodownload.
New feature: JSON output has addition 'language' key.
New feature: --postfix works without --language.
Bigfix: Rare bug in alternative subtitle writer [r189.1].
Change: --vad_alt_method shorted to --vad_method.

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.

CUDA11_v2 is the last with support for GPUs with Kepler chip.

CUDA11_v2: - cuBLAS.and.cuDNN____v11.11.3.6__v8.7.0.84
CUDA11_v3: - cuBLAS.and.cuDNN____v11.11.3.6__v8.9.6.50
CUDA11_v4: - cuBLAS.and.cuDNN____v11.11.3.6__v8.9.7.29
CUDA12_v1: - cuBLAS.and.cuDNN____v12.4.5.8___v8.9.7.29