---
title: Sam Audio Webui
emoji: 🎵
colorFrom: indigo
colorTo: pink
app_file: app.py
pinned: false
license: apache-2.0
fullWidth: true
hardware: zerogpu
sdk: gradio
sdk_version: 6.2.0 # Ensure you use a recent Gradio version compatible with Py 3.11
---

# SAM Audio WebUI

This Space hosts a WebUI for the **SAM Audio** model by Meta (Facebook), designed to segment and isolate specific sounds from audio files using text prompts.

## Features

- **Model**: Uses `facebook/sam-audio-small` for a balance of performance and resource usage.
- **ZeroGPU Support**: Optimized to run on Hugging Face ZeroGPU (A100) with automatic GPU handling.

## System Requirements

- **VRAM**: ~21.6 GB for standard loading.
- **Python**: >= 3.11 required by `perception-models` dependency.

## Acknowledgements

- Model: [facebook/sam-audio](https://huggingface.co/facebook/sam-audio)
- Library: [Hugging Face Transformers](https://huggingface.co/docs/transformers/index)