Feature: Add FunASR/SenseVoice as STT option

[LauraGPT]

Hi! Cool project running voice AI on ESP32!

Would you consider FunASR or SenseVoice as a server-side STT option?

Why?

• Ultra-low latency — SenseVoice-Small: ~70ms for 10s audio
• WebSocket server — FunASR provides a production-ready WebSocket server that ESP32 can connect to
• Streaming — Paraformer-streaming processes audio frame-by-frame
• Self-hosted — No API costs, fully offline server
• 50+ languages — Apache 2.0

WebSocket server for embedded clients

# Start server that ESP32 can connect to
funasr-wss-server --model paraformer-zh-streaming --port 10095

References

• FunASR: https://github.com/modelscope/FunASR (16K+ stars)
• SenseVoice: https://github.com/FunAudioLLM/SenseVoice (8K+ stars)
• Server: https://github.com/modelscope/FunASR/tree/main/runtime