Spaces:
Runtime error
Runtime error
Peter Michael Gits
Claude
Use official HuggingFace documentation approach to override model detection
2a50bb0 |
Download README.md from pgits/stt-gpu-service-python-v4: direct link, hf CLI and curl.
- Browser
- Download file 690 Bytes
-
https://huggingface.co/spaces/pgits/stt-gpu-service-python-v4/resolve/main/README.md
- Command line
-
hf download hf://spaces/pgits/stt-gpu-service-python-v4/README.md
-
curl -L -o README.md https://huggingface.co/spaces/pgits/stt-gpu-service-python-v4/resolve/main/README.md
690 Bytes
| title: STT GPU Service Python v4 | |
| emoji: 🎙️ | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: docker | |
| app_port: 7860 | |
| hardware: l4 | |
| sleep_time_timeout: 1800 | |
| suggested_storage: small | |
| pinned: false | |
| app_file: app.py | |
| models: [] | |
| datasets: [] | |
| # STT GPU Service Python v4 | |
| Real-time WebSocket STT streaming service using full Moshi model. | |
| ## Features | |
| - WebSocket streaming (80ms chunks at 24kHz) | |
| - REST API endpoints | |
| - FastAPI backend with real-time transcription | |
| - L4 GPU acceleration (30GB VRAM) | |
| - Full Moshi model for high-quality STT | |
| ## Endpoints | |
| - `/` - Web interface for testing | |
| - `/ws/stream` - WebSocket streaming endpoint | |
| - `/api/transcribe` - REST API endpoint | |
| - `/health` - Health check |