ONNX | Home

Vibe. - Transcribe audio / video offline using OpenAI Whisper

Open Neural Network Exchange

The open standard for machine learning interoperability

ONNX is an open format built to represent machine learning models. ONNX defines a common set of operators - the building blocks of machine learning and deep learning models - and a common file format to enable AI developers to use models with a variety of frameworks, tools, runtimes, and compilers. LEARN MORE

KEY BENEFITS

Interoperability

Develop in your preferred framework without worrying about downstream inferencing implications. ONNX enables you to use your preferred framework with your chosen inference engine.

Hardware Access

ONNX makes it easier to access hardware optimizations. Use ONNX-compatible runtimes and libraries designed to maximize performance across hardware.

COMMUNITY

ONNX is a community project.

Our active community thrives under our open governance structure, which provides transparency and inclusion. We encourage you to engage and contribute.


ABBYY Aizon Alibaba AMD Arm AWS AXera Baidu Beckhoff BITMAIN Cadence CEVA ClearBlade Datakalab Facebook Furiosa Graiphic GraphCore Groq Hababa Hailo Hewlett Packard Huawei Hugging Face IBM Idein Intel AI Kalray MathWorks Maxar Mediatek Xiaomi Microsoft MosaicML NVIDIA NXP OctoML Oracle Preferred Networks Recogni Siemens Sony Qualcomm QuantCo SAS SenseTime Skymizer Synopsys Tencent TSINGMICRO Unity Verizon Media VMware Wolfram Yandex Zama Zetane


WE ARE AN LFAI GRADUATE PROJECT

LFAI GRADUATE PROJECT

NEWS AND ANNOUNCEMENTS

Recordings of the 2025 ONNX Community Meetup online

Recordings could be found at…

List of candidates for ONNX Steering Committee election.

Active contributors to the ONNX project will be requested to vote from May 12 to May 19th. Elected Steering…