whisper-openvino
A fork of OpenAI's Whisper speech recognition models optimized with OpenVINO backend for faster CPU inference.
What is whisper-openvino?
Whisper OpenVINO is an optimized fork of OpenAI's Whisper speech recognition system that uses Intel's OpenVINO runtime to accelerate transcription on CPU hardware. It solves the problem of slow Whisper inference on consumer CPUs by providing hardware-optimized models that maintain full compatibility with the original API. The project enables faster speech-to-text conversion without requiring GPU acceleration.
Developers and researchers who need to run Whisper speech recognition efficiently on Intel CPU-based systems, particularly those working with transcription applications on laptops, servers, or edge devices without dedicated GPUs.
Developers choose Whisper OpenVINO because it provides significant performance improvements over the original Whisper on CPU hardware while maintaining 100% API compatibility. The unique selling point is the drop-in replacement capability that requires no code changes while offering ~40% faster transcription times.
Overview
openvino version of openai/whisper
Use Cases
Best For
- Transcribing long audio files on CPU-only systems
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
