Clean up noisy speech in real time with DPDFNet - open-source streaming speech enhancement for research, audio apps, and edge devices. Includes pretrained models, PyTorch code, ONNX/TFLite inference, 8/16/48 kHz support, and live demos.
audio deep-learning pytorch low-latency speech-processing audio-processing streaming-audio real-time-audio speech-enhancement speech-denoising onnx tflite edge-ai noise-suppression audio-denoising voice-enhancement deepfilternet deepfilternet2 dual-path-rnn dprnn
-
Updated
Sep 9, 2026 - Python