Nexa AI recently unveiled its new OmniAudio-2.6B audio language model, designed to meet the efficient deployment demands of edge devices. Unlike traditional architectures that separate automatic speech recognition (ASR) and language models, OmniAudio-2.6B integrates Gemma-2-2b, Whisper Turbo, and a custom projector into a unified framework. This design eliminates the inefficiencies and delays associated with linking various components in traditional systems, making it especially suitable for resource-constrained computing.

1. MediaTek collaborates with OPPO to build a lightweight large model edge-side deployment solution. 2. Based on AndesGPT, uses 4-bit quantization technology for edge-side large model performance optimization. 3. The new round of public testing for XiaoBu Assistant is launched, built on AndesGPT. 4. AndesGPT is OPPO's self-trained generative large language model. 5. AndesGPT will continue to enhance the AI capabilities of OPPO's XiaoBu for more product implementations.