README.md

metadata

title: VoiceWarp Real-Time Voice Translation
emoji: 🐨
colorFrom: blue
colorTo: green
sdk: gradio
app_port: 7860
pinned: false
license: apache-2.0
sdk_version: 6.9.0
python_version: '3.11'

🎙️ VoiceWarp — Real-Time Voice Translation

How to deploy on HuggingFace Spaces

1. Create a new Space at https://huggingface.co/spaces

• SDK: Docker
• Hardware: CPU Basic (free) or T4 GPU (faster)

2. Upload these files keeping the static/ folder:

README.md
app.py
pipeline.py
requirements.txt
Dockerfile
static/index.html

3. Wait ~10 minutes for the build, then open your Space URL.

How to use

1. Select your speaking language and target language
2. Click Start Recording — speak your sentence — click Stop Recording
3. Click Translate Now
4. Watch the progress bar — hear yourself translated

Models

Model	Task	Size
faster-whisper small	Speech recognition	~500MB
facebook/nllb-200-distilled-600M	Translation	600MB
coqui/XTTS-v2	Voice cloning	~1.8GB

Run locally

python3.11 -m venv venv && source venv/bin/activate
pip install -r requirements.txt
python app.py
# open http://localhost:7860