Nvidia-Gpu on Noureddine RAMDIhttps://ramdi.fr/tags/nvidia-gpu/Recent content in Nvidia-Gpu on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000Flexible chunk-size Whisper inference with optimized on-device engines in TheWhisperhttps://ramdi.fr/github-stars/flexible-chunk-size-whisper-inference-with-optimized-on-device-engines-in-thewhisper/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/flexible-chunk-size-whisper-inference-with-optimized-on-device-engines-in-thewhisper/TheWhisper breaks Whisper’s 30s fixed chunk limit by supporting flexible chunk sizes for streaming speech-to-text. It provides optimized CoreML and CUDA engines for Apple Silicon and NVIDIA GPUs.