Whisper STT (Stark Edition)
A high-performance bridge to a local Whisper STT server. Designed for real-time conversational AI agents where every millisecond counts.
Architecture
Redirects all transcription requests to a high-performance Sphinx GPU server at http://sphinx.espuny.net:5000.
Usage
{baseDir}/scripts/whisper-bridge.sh /path/to/audio.mp3 large-v3-turbo en
Key Metrics
- Latency: ~0.2s for standard voice commands.
- Accuracy: High (Whisper large-v3-turbo).
- Concurrency: Hybrid thread-managed GPU architecture.
Scan to join WeChat group