vui
https://github.com/fluxions-ai/vui
Small Conversational speech models that can run on device
Installation
uv pip install -e .
Demo
python demo.py
Models
Vui.BASE is base checkpoint trained on 40k hours of audio conversations Vui.ABRAHAM is a single speaker model that can reply with context awareness. Vui.COHOST is checkpoint with two speakers that can talk to each other.
Voice Cloning
You can clone with the base model quite well but it's not perfect as hasn't seen that much audio / wasn't trained for long
FAQ
- Was developed with on two 4090's https://x.com/harrycblum/status/1752698806184063153
- Hallucinations: yes the model does hallucinate, but this is the best I could do with limited resources! :(
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support