whisper.cpp is a high-performance C/C++ implementation of OpenAI’s Whisper automatic speech recognition model.
The project is designed for efficient local inference without requiring the original Python and PyTorch software stack, making Whisper practical on systems ranging from conventional Linux desktops and servers to Raspberry Pi boards, mobile devices and WebAssembly environments. Its implementation builds on ggml and places considerable emphasis on portability, low runtime overhead and hardware-specific acceleration.
Users can run transcription entirely on the CPU or take advantage of several GPU and accelerator backends. Models are converted to ggml format, with quantization available when reduced memory consumption and storage requirements are important.
This is free and open source software.
Key Features
- High-performance local inference using OpenAI Whisper speech recognition models.
- Plain C and C++ implementation with a lightweight runtime architecture.
- CPU-only transcription without requiring a discrete graphics processor.
- Integer model quantization to reduce memory consumption and model file sizes.
- Mixed F16 and F32 precision for balancing computational efficiency and numerical requirements.
- AVX instruction support for accelerating inference on compatible x86 processors.
- ARM NEON and Accelerate framework optimizations for Apple Silicon systems.
- Metal backend for executing Whisper inference efficiently on Apple GPUs.
- Core ML support for running encoder inference on Apple’s Neural Engine.
- CUDA support using cuBLAS and custom kernels on NVIDIA GPUs.
- ROCm/HIP acceleration for supported AMD graphics hardware.
- Vulkan backend offering cross-vendor GPU acceleration on compatible hardware.
- OpenVINO integration for acceleration on supported Intel CPUs and GPUs.
- POWER VSX optimizations for POWER9 and POWER10 systems.
- Voice activity detection for identifying speech regions before transcription.
- C-style API suitable for embedding speech recognition into other applications.
- Command-line transcription utility with configurable models and inference options.
- Cross-platform support – runs on Linux, FreeBSD, Windows, macOS, Android, iOS and WebAssembly deployments.
- Runs on resource-constrained hardware including Raspberry Pi systems.
- Runtime design avoids memory allocations during inference once processing has started.
Website: github.com/ggml-org/whisper.cpp
Support:
Developer: ggml-org
License: MIT License
whisper.cpp is written in C++ and C. Learn C++ with our recommended free books and free tutorials. Learn C with our recommended free books and free tutorials.
Related Software
| Speech Recognition Tools | |
|---|---|
| Whisper | Automatic speech recognition (system trained on 680,000 hours of data |
| Flashlight | Fast, flexible machine learning library written entirely in C++. |
| Coqui STT | Deep-learning toolkit for training and deploying speech-to-text models |
| Kaldi | C++ toolkit designed for speech recognition researchers. |
| SpeechBrain | All-in-one conversational AI toolkit based on PyTorch |
| Handy | Offline speech-to-text application |
| ESPnet | End-to-End speech processing toolkit |
| deepspeech.pytorch | Implementation of DeepSpeech2 using Baidu Warp-CTC. |
| Whispering | Transcription application with global speech-to-text functionality |
| Julius | Two-pass large vocabulary continuous speech recognition engine |
| CMUSphinx | Speech recognition system for mobile and server applications |
| Simon | Flexible speech recognition software |
| hyprwhspr | Native speech-to-text designed for Arch / Omarchy |
| ostt | Open Speech-to-Text |
| DeepSpeech | TensorFlow implementation of Baidu's DeepSpeech architecture. |
| OpenSeq2Seq | TensorFlow-based toolkit for sequence-to-sequence models |
| Eesen | End-to-End Speech Recognition |
Read our verdict in the software roundup.
 Explore our comprehensive directory of recommended free and open source software. Our carefully curated collection spans every major software category.This directory is part of our ongoing series of informative articles for Linux enthusiasts. It features hundreds of detailed reviews, along with open source alternatives to proprietary solutions from major corporations such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk. You’ll also find interesting projects to try, hardware coverage, free programming books and tutorials, and much more. Discovered a useful open source Linux program that we haven’t covered yet? Let us know by completing this form. |
Please read our Comment Policy before commenting.