Voice dialogue model "Haru 4B" that can speak naturally like a human released for free
A voice dialogue model "Haru 4B" that can produce natural vocalizations like a human and respond to backchanneling and interruptions has appeared. Announced by higurashi on November 13, the open weights of the pre-trained base model were released for free on Hugging Face under the Apache License 2.0. Inference code is also released on GitHub.
A voice dialogue model "Haru 4B" that can produce natural vocalizations like a human and respond to backchanneling and interruptions has appeared.
Announced by higurashi on November 13, the open weights of the pre-trained base model were released for free on Hugging Face under the Apache License 2.0. Inference code is also released on GitHub.
This item is a summary. The full, checkable version is at the original source:
Read the original at PC Watch ↗