AI Briefing#onnx
The latest AI and developer news about #onnx, with the original source and a short summary.
The latest AI and developer news about #onnx, with the original source and a short summary.
The release includes three model sizes ranging from 7.2M to 82M parameters, all supporting 24 kHz audio output and CPU-only execution via int8 ONNX weights.
The project uses a 21.7 MB iSTFTNet vocoder for mobile devices and a 27.9 MB HiFi-GAN for desktops to achieve 0.75x real-time factor synthesis.
The new pipeline reduces median post-push scan execution time by 86% and improves user acceptance by 11.5% compared to the previous LLM approach.
Neuphonic has open sourced NeuDecide, a 43 MB audio-to-tool model that achieves 72.4% tool accuracy on SLURP benchmarks without transcription, running efficiently on a single CPU thread.
The open-source tool hayamimi has been released, generating real-time multilingual subtitles using only the CPU without GPU dependencies.
This guide demonstrates how to consistently deploy AI models to edge devices by combining the DEEPX DX-M1 NPU with AWS IoT.
A fine-tuning toolkit has been released that lets the ultra-compact TTS model Inflect-Nano-v2 be trained on a specific voice or language.
OpenCV 5 has been released, significantly modernizing the DNN engine and greatly strengthening ONNX support.
A local agent memory engine that re-weights memories based on failure/success feedback.
Pocket LLM v1.3.0 released, supporting local LLM chat on Android.
In collaboration with AMD, ONNX-optimized versions of Stable Diffusion models were released, optimized for AMD Radeon GPUs and Ryzen AI APUs.
Kakaopay shared its process of comparing and optimizing frameworks to improve the consistency and performance of model serving.
Explains how to convert Transformers models to ONNX format and optimize inference performance using Hugging Face Optimum.