Model reference · open weights
RE-USE is an open-weight audio or speech model from nvidia, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
<span style="color:#76b900;"🤫 RE-USE: Multilingual Universal Speech Enhancement</span Model Overview Description In universal speech enhancement, the goal is to restore the quality of diverse degraded speech while preserving fidelity, ensuring that all other factors remain unchanged, e.g., linguistic content, speaker identity, emotion, accent, and other paralinguistic attributes. Inspired by the distortion–perception trade-off theory, our proposed single model achieves a good balance between these two objectives and has the following desirable properties: - Robustness to diverse degradations, including additive noise, reverberation, clipping, bandwidth limitation, codec artifacts, packet loss and low-quality mics . - Support for multiple input sampling rates, including 8, 16, 22.05, 24, 32, 44.1, and 48 kHz. - Strong language-agnostic capability, enabling effective performance across different languages. This model is for research and development only. Usage Directly try our Gradio Interactive Demo by uploading your noisy audio/video !! Environment Setup 1. (For Mamba setup)Pre-built Docker environments can be downloaded here to simplify Mamba setup. 2. If you need bandwidth extension: 3. Download and navigate to the HuggingFace repository: Inference Follow the simple steps below to generate enhanced speech using our model: 1. Place your noisy speech files in the folder noisyaudio/ 2. Run the following command: 3. The enhanced speech files will be saved in enhancedaudio/. That's all ! Note: a. You can enable bandwidth extension by setting the target bandwidth using the BWE argument in the script. If your noisy speech files are long and may cause GPU out-of-memory (OOM) errors, please use the following procedure instead: 1. Place your long noisy speech files in the folder longnoisyaudio/ 2. Run the following command: 3. The enhanced speech files will be saved in Longenhancedaudio/. Note: a. You can enable bandwidth extension by setting the target bandwidth using the BWE argument in the script. b. You can also configure the chunksizeinseconds and hoplengthportion directly in the script. License/Terms of Use This model is released under the NVIDIA One-Way Noncommer
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nvidia |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 10M |
| Variants | 1 |
| Runs with | mamba-ssm |
| Released | 2026-03-17 |
| Popularity | 17k downloads / month |
| Likes | 98 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| RE-USE | 10M | BF16 | ~0 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys re-use for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (re-use below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="re-use" -F file=@audio.mp3
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗