|
--- |
|
title: Voice Safety Classifier Demo |
|
emoji: 📚 |
|
colorFrom: blue |
|
colorTo: red |
|
sdk: gradio |
|
sdk_version: 5.23.3 |
|
app_file: app.py |
|
pinned: false |
|
license: apache-2.0 |
|
short_description: Demo deployment for voice safety classifier |
|
--- |
|
|
|
# Voice Safety Classifier Demo |
|
|
|
This is a demo application for the [Roblox Voice Safety Classifier v2](https://huggingface.co./Roblox/voice-safety-classifier-v2) model. |
|
|
|
## Model Information |
|
|
|
The Voice Safety Classifier is designed to detect potentially unsafe content in audio. It can classify audio into various safety categories to help identify problematic content. |
|
|
|
## Usage |
|
|
|
1. Upload an audio file or record audio directly in your browser |
|
2. The model will process the audio and return classification results |
|
3. Results are displayed with confidence scores for each category |
|
|
|
## Technical Details |
|
|
|
This demo uses: |
|
- Hugging Face Transformers |
|
- Gradio for the web interface |
|
- PyTorch and TorchAudio for audio processing |
|
|
|
## License |
|
|
|
This demo uses the Roblox Voice Safety Classifier v2 model. Please refer to the [model card](https://huggingface.co./Roblox/voice-safety-classifier-v2) for licensing information. |
|
|
