---
title: Fragmenta
emoji: 🎵
colorFrom: purple
colorTo: blue
sdk: docker
app_port: 7860
pinned: false
license: apache-2.0
---

# Fragmenta — AI Audio Generation & Fine-Tuning

Generate and fine-tune audio from text prompts using Stable Audio Open.

**Hardware:** cpu-upgrade (CPU)

## Getting Started

1. Upload your model weights (`.safetensors`) to `models/pretrained/` in the Space Files tab.
   - `stable-audio-open-small-model.safetensors` (recommended for CPU)
   - `stable-audio-open-model.safetensors` (full model, recommended for GPU)
2. The Space will auto-rebuild after the upload.
3. Use the **Data Processing** tab to upload audio + prompts.
4. Use the **Training** tab to fine-tune.
5. Use the **Generation** tab to generate audio.