Skip to content
SPECIFICTION
Get listed

DPDFNet

github.com

Free plan WindowsmacOSLinuxiOSAndroidAPI
Visit github.com
Spec score 8.0 #13 of 35 in AI Speech Enhancement Software

What it is

DPDFNet is a free, open-source model for reducing noise in single-channel speech from recordings, live streams, and edge-device applications. It supports offline processing and streaming, and extends DeepFilterNet2 with dual-path encoder blocks and an always-on fine-tuning approach intended to reduce over-attenuation. Pretrained variants support 8, 16, and 48 kHz audio. The repository includes PyTorch code and ONNX and TFLite inference models, with command-line, Python, and stateful streaming interfaces. Streaming buffers about 20 ms before the first enhanced output, then adds about 10 ms of delay for later blocks. A hosted Gradio demo and audio examples are linked from the project page. Listed community integrations include sherpa-onnx, OBS Studio, VST3 and LADSPA plugins, Core ML ports, and WebAssembly. The project page reports real-time DPDFNet-4 deployment on Ceva-NeuPro-Nano edge NPUs in a benchmark setup using int8 weights and int16 activations. The software is under Apache License 2.0. Model files are not bundled in the source repository; it provides commands to download checkpoints and ONNX or TFLite models from Hugging Face.

Spec sheet

Purpose
DPDFNet is a causal, single-channel speech-enhancement model for cleaning noisy speech in recordings, live streams, and edge-device applications.Read 8 Oct 2026 · github.com
Deployment
The project page reports real-time deployment of DPDFNet-4 on Ceva-NeuPro-Nano edge NPUs, using int8 weights and int16 activations in the benchmark setup.Read 8 Oct 2026 · ceva-ip.github.io
Integrations
The maker's community directory lists integrations including sherpa-onnx, OBS Studio, VST3 and LADSPA plugins, Core ML ports, and a WebAssembly implementation.Read 8 Oct 2026 · github.com
Support
The repository directs users to open an issue or submit a pull request to add a DPDFNet integration to its community directory.Read 8 Oct 2026 · github.com
License
The repository provides the software under the Apache License 2.0.Read 8 Oct 2026 · github.com
Headquarters
Rockville, Maryland, USARead 28 Sep 2026 · github.com
Founded
1999Read 28 Sep 2026 · github.com
Architecture
It extends DeepFilterNet2 with dual-path encoder blocks and an always-on fine-tuning approach designed to reduce over-attenuation.Read 8 Oct 2026 · ceva-ip.github.io
Evaluation
The paper describes an evaluation set of long, low-SNR recordings in 12 languages across everyday noise scenarios.Read 8 Oct 2026 · ceva-ip.github.io
Inference formats
The repository includes PyTorch code and ONNX and TFLite inference models.Read 8 Oct 2026 · github.com
Interfaces
The project documents a command-line interface, Python API, and stateful streaming API.Read 8 Oct 2026 · github.com
Live demo
The repository links to a hosted Gradio demo and a project page with audio examples.Read 8 Oct 2026 · github.com
Sample rates
Pretrained model variants support 8, 16, and 48 kHz audio.Read 8 Oct 2026 · github.com
Streaming latency
The streaming API buffers about 20 ms before its first enhanced output and adds about 10 ms of delay for subsequent blocks.Read 8 Oct 2026 · github.com
Use requirements
The repository says model files are not bundled in the source repository and provides commands to download checkpoints and ONNX or TFLite models from Hugging Face.Read 8 Oct 2026 · github.com

Plans and prices

Open-source DPDFNet Free Apache-2.0 licensed code and models; no commercial pricing or usage limits stated Read 8 Oct 2026 · github.com

Every DPDFNet plan and price →

Strong points and limits

Strong points

  • Supports 8, 16, and 48 kHz audio
  • Provides PyTorch, ONNX, and TFLite options
  • Includes command-line, Python, and streaming interfaces
  • Apache License 2.0
  • Listed integrations include OBS Studio and WebAssembly

Limits

  • Model files are not bundled in the source repository
  • Streaming buffers about 20 ms before first output

Who it suits

DPDFNet suits developers and teams building speech enhancement into recording, streaming, or edge-device workflows. Its documented command-line, Python, and streaming interfaces offer several ways to use the model.

Verdict

DPDFNet provides multiple inference formats and interfaces for offline and streaming speech enhancement, with code under Apache License 2.0. Users need to download model files separately, and streaming has stated buffering and block delays.

Where Specifiction places it

Alternatives to DPDFNetAll alternatives →