Benchmark Snapshot (PyTorch vs qwen3-tts.cpp): Basic 3.19x faster, Clone 4.07x faster. Peak RSS delta: Basic +19.0%, Clone +7.7%. C++ inference for Qwen3-TTS using the GGML tensor library. Runs the ...

This repo contains code for our DCASE 2025 task3 proposed method : Stereo sound event localization and detection based on PSELDnet pretraining and BiMamba sequence modeling [1]. For more information, ...