has any one used dtln noise suppression? I have integrated it and testing in livekit playground but getting no logs to confirm if dtln is working. Is there any other way to test it?

it's depend on how dtln is added to your pipeline , the pipeline should like this Room audio (raw frames) ↓ filtered_audio() ← Model runs here, frame by frame ↓ super().stt_node() ← STT receives clean audio stt_node is the LiveKit agent's hook that receives audio before it's transcribed. By overriding it and wrapping the audio async generator with filtered_audio(), every frame is denoised before it reaches the STT model. The STT never sees the raw noisy audio.