FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learning
Paper • 2601.16483 • Published
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
FlowSE & FlowSE-GRPO: Conditional Flow Matching for Speech Enhancement
This project is a personal implementation of the FlowSE-GRPO work.
Main references: FlowSE: https://arxiv.org/abs/2505.19476; FlowSE-GRPO: https://arxiv.org/abs/2601.16483; FlowGRPO: https://arxiv.org/abs/2505.05470; GRPO-GUARD: https://arxiv.org/abs/2510.22319
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Papers for adzzuki/FlowSE-GRPOGUARD
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
Paper • 2510.22319 • Published • 3
FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
Paper • 2505.19476 • Published
Flow-GRPO: Training Flow Matching Models via Online RL
Paper • 2505.05470 • Published • 88