Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Mati83moniΒ 
posted an update 3 days ago
Post
90
Kos: a Polish voice assistant that's allowed to say "I'm not sure" 🐦

Kos is a free Polish voice assistant running on ZeroGPU: Silero VAD β†’ Whisper large-v3 β†’ PLLuM-12B (EXL3) β†’ TTS. It's a cascade, not a native speech-to-speech model.

The interesting part is what happens between "the model wrote a sentence" and "the sentence is spoken":

β€’ math, units, exchange rates (NBP) and weather are computed by code, not by the LLM
β€’ facts go to Polish Wikipedia/Wikidata first, with sources you can check
β€’ free-chat answers are buffered and rejected if they contain an unsourced number, a fake citation or a false "I have no internet"
β€’ a rejected answer is never spoken: Kos looks it up or says it isn't sure

Voice: my own cloned voice on Cartesia. When its daily/monthly limit runs out, Kos switches automatically to Chatterbox, then Piper. It still answers, it just sounds different.

Limits: it's a 12B model, so small talk can still be wrong. Polish only. ZeroGPU quota is shared by all visitors.

Try it (allow the mic, speak Polish, headphones work best):
Mati83moni/kos-pl

If it answers something wrong, tell me in the Space's Community tab: what you said, what Kos replied. Those cases become regression tests.

Full write-up with the architecture, the answer checks and the lessons from running it publicly:
https://huggingface.co/blog/Mati83moni/kos-a-polish-voice-assistant-that-is-allowed-to-sa

In this post