ceva-ip/DPDFNet

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.

语言：Python · GitHub 星标：174 · Fork：19

话题：audio · audio-denoising · audio-processing · deep-learning · deepfilternet · deepfilternet2 · dprnn · dual-path-rnn

在 GitHub 上查看原仓库