olive-42404600·2 events·first seen Aliases: Olive
OLIVE (Online Latent prediction with Invariant Views and rEconstruction) is a new self-supervised speech representation learning framework that combines view-augmented masked latent prediction with waveform reconstruction under a unified objective. The reconstruction objective constrains early encoder features to retain signal-level information, while masked latent prediction shapes later contextual representations toward invariance. The authors report improvements on generation and speaker tasks, competitive performance on recognition and semantic tasks, and better waveform reconstruction compared to prior SSL approaches.
This Hugging Face blog post details how to accelerate Stable Diffusion Turbo and SDXL Turbo inference using ONNX Runtime and Microsoft's Olive optimization toolkit. The post covers the workflow for converting and optimizing diffusion models for faster deployment. This is a practical inference optimization guide targeting practitioners deploying image generation models.