README.md

---
title: SidonSamples
emoji: 🐋
colorFrom: yellow
colorTo: indigo
sdk: static
pinned: false
license: mit
short_description: Demo page for Sidon speech restoration model
---

## Usage

- Add your audio files to `assets/audio/`:
  - `assets/audio/sample1_noisy.wav`
  - `assets/audio/sample1_restored.wav`
- Generate mel-spectrogram images (optional helper in `tools/`):
  - Install deps: `pip install librosa matplotlib`
  - Create images:
    - `python tools/make_mel_images.py assets/audio/sample1_noisy.wav assets/mels/sample1_noisy.png`
    - `python tools/make_mel_images.py assets/audio/sample1_restored.wav assets/mels/sample1_restored.png`
- Open `index.html` and duplicate one of the “Sample” boxes to add more items. Update the file paths per sample.

The page uses Bulma CSS and standard HTML5 audio elements, so no backend is required. Serve statically (e.g., `python -m http.server`).
# Website License
<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.