Hertz-dev: an open-source, first-of-its-kind base model for full-duplex conversational audio. It's an 8.5B parameter transformer trained on 20 million unique hours of high-quality audio data. it is a base model, without fine-tuning, RLHF, or instruction-following behavior pic.twitter.com/BtyFRQk0it
— Chubby♨️ (@kimmonismus) 4 novembre 2024
Hertz-dev: an open-source, first-of-its-kind base model for full-duplex conversational audio. It's an 8.5B parameter transformer trained on 20 million unique hours of high-quality audio data. it is a base model, without fine-tuning, RLHF, or instruction-following behavior