OWLS: Scaling Laws for Speech Recognition and Translation Collection 🦉 A suite of Whisper-style models from 250M to 18B parameters. Trained on up to 360K hours of data. • 6 items • Updated 1 day ago • 2
Open Whisper-style Speech Models (OWSM) Collection Fully open Whisper-style speech foundation models developed by CMU WAVLab: https://www.wavlab.org/activities/2024/owsm/ • 15 items • Updated 21 days ago • 5
Slamming: Training a Speech Language Model on One GPU in a Day Paper • 2502.15814 • Published 7 days ago • 49
Running 1.66k 1.66k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
Presumed Cultural Identity: How Names Shape LLM Responses Paper • 2502.11995 • Published 9 days ago • 10
view article Article Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥 9 days ago • 89