Hugging Face's logo

Spaces:
Wataru
/
SidonSamples
Running

App Files Community
SidonSamples / README.md
Wataru's picture
Wataru
Merge origin/main into main with --allow-unrelated-histories; resolve conflicts preferring local
1fba6cf
preview code
|
raw
history blame
1.3 kB
metadata
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

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.