GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published 11 days ago • 197
view reply https://huggingface.co/primeline/parakeet-primeline Of course here is the link to the model :) @bjoernp @maxidl @DavidGF @Behrens
Running on Zero German Speech Recognition Model Comparison 🔥 Compare german open source speech recognition models