ONNX Runtime
AssessTools
An inference runtime for executing ONNX machine learning models.
Why it's here
Placed in Assess: 5 article(s) of evidence from 3 source(s), led by framework updates, with 1 in the last 30 days. Confidence 62%.
Evidence (5)
- 5Hacker News·7/26/2026model_releaseInflect-Micro-v2 Brings Complete Local Voice Models
Inflect-Micro-v2 introduces complete local text-to-waveform speech models in 3.96M and 9.36M parameter variants. Official releases are available for PyTorch and ONNX Runtime, making the models easier to test and deploy locally.
- 5Hugging Face Blog·6/23/2026framework_updateTransformers.js tests proposed Cross-Origin Storage API for shared caching
Hugging Face describes experiments in Transformers.js with the proposed Cross-Origin Storage API to reduce duplicated downloads and storage across different origins. The post shows that model files and shared WebAssembly runtime assets can be cached once and reused, instead of being fetched again for each site using the same resources.
- 6Simon Willison·6/22/2026researchPorting Moebius image inpainting to the browser with WebGPU
Simon Willison describes porting the Moebius 0.2B image inpainting model from a PyTorch/NVIDIA CUDA setup to run in the browser. He used Claude Code, ONNX Runtime Web, and WebGPU to build a working demo that lets users upload an image, mask regions, and have the model fill them in.
- 6Hugging Face Blog·6/22/2026model_releasePP-OCRv6 Brings 50-Language OCR to Hugging Face
Hugging Face blog introduced PP-OCRv6, the latest PaddleOCR model family for detection and recognition across documents, screenshots, multilingual images, and scene text. The lineup ranges from 1.5M to 34.5M parameters, with the small and medium models supporting 50 languages and the medium model improving benchmark scores over PP-OCRv5_server.
- 7Hugging Face Blog·2/9/2026framework_updateTransformers.js v4 arrives on npm
Transformers.js v4 is now available on npm after a year of development. The release introduces a rewritten WebGPU runtime in C++, broader model support, and performance improvements that extend to browsers, Node, Bun, and Deno.