https://pypi.org/project/whisper-gpu-kit/ Recent updates to the Python Package Index for whisper-gpu-kit en https://pypi.org/project/whisper-gpu-kit/0.1.1/ GPU (faster-whisper) transcription primitives: cuDNN/cuBLAS preload, lazy model cache, GPU-OOM detection with CPU fallback, plus VTT/SRT caption parsing Wed, 14 Oct 2026 06:40:07 GMT