| ---
|
| license: other
|
| license_name: nvidia-one-way-noncommercial-and-mit-apache
|
| license_link: LICENSE
|
| base_model: nvidia/Real-time_RE-USE
|
| pipeline_tag: audio-to-audio
|
| library_name: hush-ai
|
| tags:
|
| - speech-enhancement
|
| - noise-suppression
|
| - noise-cancellation
|
| - real-time
|
| - streaming
|
| - mamba
|
| - deepfilternet
|
| - rust
|
| - cpu
|
| - on-device
|
| ---
|
|
|
| <p align="center">
|
| <img src="icon.png" width="104" alt="Hush AI">
|
| </p>
|
|
|
| <h1 align="center">Hush AI · voice models</h1>
|
|
|
| <p align="center">
|
| The model files that the <a href="https://github.com/alshell7/hush-ai"><b>Hush AI</b></a> app downloads:
|
| free, open-source, on-device noise cancellation for every app.
|
| </p>
|
|
|
| <p align="center">
|
| <a href="https://github.com/alshell7/hush-ai/releases/latest"><b>Download the app</b></a> ·
|
| <a href="https://alshell7.github.io/hush-ai/"><b>Website</b></a> ·
|
| <a href="https://github.com/alshell7/hush-ai"><b>GitHub</b></a>
|
| </p>
|
|
|
| 
|
|
|
| ## What is here
|
|
|
| | File | Contents | License |
|
| | --- | --- | --- |
|
| | `models/DeepFilterNet3_onnx-v0.5.6.tar.gz` | [DeepFilterNet 3](https://github.com/Rikorose/DeepFilterNet) by Hendrik Schröter, from release `v0.5.6`, **unchanged** (ONNX encoder and two decoders, 8 MB) | MIT or Apache-2.0 |
|
| | `models/realtime-reuse-4c0c186.safetensors` | NVIDIA [Real-time RE-USE](https://huggingface.co/nvidia/Real-time_RE-USE) weights, revision `4c0c186`, **unchanged** (FP32, 13.5 M parameters, 54 MB) | NVIDIA One-Way Noncommercial |
|
| | `models/SHA256SUMS` | SHA-256 of both model files | |
|
| | `samples/noisy.mp3`, `samples/hush.mp3` | NVIDIA's sample recording, before and after Hush AI | NVIDIA One-Way Noncommercial |
|
|
|
| The app checks the SHA-256 before it uses a file. If this mirror is unreachable, it
|
| downloads the same file from its original source at the same version.
|
|
|
| ## How Hush AI runs the models
|
|
|
| [Hush AI](https://github.com/alshell7/hush-ai) has two engines, and you can switch between them
|
| in the app. Both run on the CPU, with no Python, GPU or network:
|
|
|
| - **DeepFilterNet 3**: the official Rust inference (libDF with tract), 48 kHz, 10 ms frames.
|
| Light on the CPU, and its license allows commercial use.
|
| - **NVIDIA Real-time RE-USE**: a native Rust port of NVIDIA's Mamba model, 20 ms frames.
|
|
|
| RE-USE quality settings in the app:
|
|
|
| | Quality | Model setting | Apple M1, 2 threads (p99 per 20 ms frame) |
|
| | --- | --- | ---: |
|
| | Light (app default) | 16 kHz, 3 layers | 11.7 ms |
|
| | Balanced | 24 kHz, 4 layers | 21.3 ms |
|
| | Studio | 48 kHz, 3 layers | 36.8 ms |
|
|
|
| - **Delay:** about 60–80 ms plus device buffers.
|
| - **Accuracy:** NVIDIA's seven GPU regression cases pass in CI on Windows, macOS and Linux.
|
| The CPU output matches NVIDIA's GPU reference at 113–118 dB waveform SNR on short speech.
|
| - **Comparison:** measured against DeepFilterNet 3 and RNNoise on VoiceBank-DEMAND in
|
| [COMPARISON.md](https://github.com/alshell7/hush-ai/blob/main/docs/COMPARISON.md).
|
|
|
| Use the RE-USE weights from Rust with the [`hush-core`](https://github.com/alshell7/hush-ai/tree/main/crates/hush-core) crate:
|
|
|
| ```rust
|
| let mut denoiser = hush_core::Denoiser::with_config(
|
| "models/realtime-reuse-4c0c186.safetensors",
|
| hush_core::Config { layers: 3, sample_rate: 16_000, look_ahead: 0 },
|
| )?;
|
| let mut clean = Vec::new();
|
| denoiser.process_into(&noisy_chunk, &mut clean)?;
|
| ```
|
|
|
| ## Licenses
|
|
|
| - **DeepFilterNet 3** (`models/DeepFilterNet3_onnx-v0.5.6.tar.gz`): © Hendrik Schröter, MIT
|
| ([LICENSE-DeepFilterNet-MIT](models/LICENSE-DeepFilterNet-MIT)) or Apache-2.0
|
| ([LICENSE-DeepFilterNet-APACHE](models/LICENSE-DeepFilterNet-APACHE)), at your option.
|
| Commercial use is allowed. Paper: Schröter et al., *DeepFilterNet: Perceptually Motivated
|
| Real-Time Speech Enhancement*, Interspeech 2023.
|
| - **Real-time RE-USE** (`models/realtime-reuse-4c0c186.safetensors`) and the samples:
|
| NVIDIA's work, redistributed unchanged under the **NVIDIA One-Way Noncommercial License**
|
| ([LICENSE](LICENSE)): **non-commercial research and educational use only**. NVIDIA
|
| Corporation and its affiliates may use them commercially. See the original
|
| [NVIDIA model card](https://huggingface.co/nvidia/Real-time_RE-USE) for the model, its
|
| training and its papers.
|
|
|
| The Hush AI app and engine are Apache-2.0. Hush AI is an independent project and is not
|
| affiliated with or endorsed by NVIDIA or the DeepFilterNet authors.
|
|
|
