whisper.cpp and whisper.rn
B is a React Native binding that allows developers to use the core C/C++ functionality provided by A within a mobile application context.
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.rn
mybigday/whisper.rn
React Native binding of whisper.cpp.
Enables on-device speech recognition with voice activity detection (VAD) and real-time transcription capabilities using optimized C++ inference. Supports hardware acceleration (Core ML on iOS, ARM NEON on Android) and includes a streaming transcriber with auto-slicing and configurable audio adapters. Pre-built binaries available for iOS; models and audio data can be loaded from files, HTTP URLs, base64, or bundled assets.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work