higurashi-ai Open-Sources Haru-4B Full-Duplex Speech Model

Written by

in

higurashi-ai has released Haru-4B, an open-source full-duplex speech model based on Qwen3.5-4B. Its weights are licensed under Apache-2.0 and available on Hugging Face, while the code has been open-sourced on GitHub.

Source:explainx.ai · Read Original

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *