Ichigo: Local real-time voice AI

Ichigo is an open-source, real-time voice AI project rebranded from llama3-s. It extends the text-based LLM's 'listening' capabilities, using an early fusion technique to combine text and audio inputs. The maintainers of Ichigo showcase ongoing progress, invite collaboration, and provide both tutorials and tools for engaging with the project.

• Ichigo features an early-fusion speech model for real-time AI interactions.
• The project is an evolution of llama3-s with improved multiturn listening.
• Maintainers provide a public writeup of each version checkpoint.
• Training and use of Ichigo are supported via Google Colab notebooks.
• Ichigo has transitioned to crowdsource speech data for development.