MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device
๐ฅ Introducing our MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device
โจ Highlights:
Match GPT-4o-202405 in vision, audio and multimodal live streaming
End-to-end real-time bilingual audio conversation
Voice cloning & emotion control
Advanced OCR & video understanding
Offline iPad-compatible multimodal live streaming
๐ Try it out:
GitHub: https://github.com/OpenBMB/MiniCPM-o
HF: https://huggingface.co/openbmb/MiniCPM-o-2_6
Demo: https://minicpm-omni-webdemo-us.modelbest.cn
Watch on YouTube โ
(saves to browser)
DeepCamp AI