sandrohanea/whisper.net
Whisper.net. Speech to text made simple using Whisper Models
What it solves
Whisper.net provides .NET bindings for OpenAI's Whisper, allowing developers to integrate high-quality speech-to-text and translation capabilities directly into C# and .NET applications without needing to write native C++ code.
How it works
It acts as a wrapper around whisper.cpp, utilizing Ggml models to perform inference. The project provides a flexible runtime system that automatically selects the best available hardware acceleration based on the platform and hardware, supporting CPU, NVIDIA CUDA (12 and 13), Apple CoreML, Intel OpenVino, and Vulkan.
Who it’s for
.NET developers who want to implement local, offline speech recognition and translation in their applications across various platforms including Windows, Linux, macOS, iOS, Android, and WebAssembly.
Highlights
- Multi-platform support: Works across desktop, mobile, and web (WASM).
- Hardware acceleration: Built-in support for CUDA, CoreML, OpenVino, and Vulkan.
- Automatic runtime selection: Transparently falls back from GPU to CPU based on available drivers and hardware.
- Easy model management: Includes a Hugging Face downloader for Ggml models and Silero VAD (Voice Activity Detection) models.
- Flexible loading: Models can be loaded from files, streams, or buffers.