whisper.cpp and whisper-cpp-server
The latter is a server wrapper built on top of the former, making them complements that work together—whisper-cpp-server adds HTTP API and real-time serving capabilities around the core whisper.cpp inference engine.
About whisper.cpp
ggml-org/whisper.cpp
Port of OpenAI's Whisper model in C/C++
Optimized for resource-constrained environments through integer quantization, mixed-precision inference (F16/F32), and zero runtime memory allocations, enabling on-device ASR on mobile and embedded platforms. Leverages the GGML inference library with multi-platform GPU acceleration via Metal, Vulkan, CUDA, and Core ML, alongside CPU-optimized SIMD paths for ARM NEON, AVX, and POWER VSX architectures. Provides a minimal C API and supports deployment across iOS, Android, WebAssembly, Raspberry Pi, and standard desktop/server platforms.
About whisper-cpp-server
litongjava/whisper-cpp-server
whisper-cpp-serve Real-time speech recognition and c+ of OpenAI's Whisper model in C/C++
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work