Test_Voice / README.md
ducnguyen1978's picture
Update README.md
9a1bae8 verified
---
title: Translation AI Agent
emoji: 🌍
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.43.1
app_file: app.py
pinned: false
license: mit
---
# 🌍 Translation AI Agent
Real-time multilingual speech-to-speech and text translation AI agent powered by state-of-the-art HuggingFace models.
## 🎯 Features
- **πŸ“ Text Translation**: Translate between 15+ languages instantly
- **🎡 Speech-to-Text**: Convert audio to text with Whisper accuracy
- **πŸ”Š Text-to-Speech**: Generate natural speech from translated text
- **πŸ”„ Speech-to-Speech**: Complete audio translation pipeline
- **πŸ”΄ Live Translation**: Real-time microphone translation
## πŸ€– AI Models
- **Translation**: `facebook/nllb-200-distilled-600M` (Meta NLLB)
- **Speech Recognition**: `openai/whisper-base` (OpenAI Whisper)
- **Text-to-Speech**: `microsoft/speecht5_tts` (Microsoft SpeechT5)
## 🌐 Supported Languages
English, Spanish, French, German, Italian, Portuguese, Russian, Japanese, Korean, Chinese, Arabic, Hindi, Vietnamese, Thai, Turkish
## πŸš€ Usage
1. **Text Translation**: Enter text and select languages
2. **Audio Translation**: Upload audio file for translation
3. **Live Translation**: Use microphone for real-time translation
## πŸ“Š Performance
- **Translation Quality**: BLEU score 25-35
- **Speech Recognition**: WER < 10% for clear audio
- **Latency**: < 2 seconds end-to-end (GPU)
Built with ❀️ using HuggingFace Transformers, Gradio, and PyTorch.