#开源模型
3 tutorials, projects and news items tagged 开源模型.
Ant Group's inclusionAI team has open-sourced Ming-3.0-audio-flash under the MIT license, a speech model that listens to audio directly for recognition, Q&A, long recording analysis, and spoken replies. It ranks first on the Artificial Analysis speech reasoning leaderboard with 99.8%, though second place is only 0.1 points behind. The post covers the parameters and GPU requirements of the Flash and Tiny versions and includes a prompt that lets your AI agent judge whether it is worth trying.
Apple has released FastFrames, an open-source video generation model in 1.3 billion and 14 billion parameter sizes, built on Wan2.1 for speed. Each frame takes tens of milliseconds, so the picture responds as soon as you press an arrow key, and a 16 times faster LingBot 1.3B demo is included. The speed was measured on NVIDIA B200 data center GPUs that ordinary computers can't match, and the weights are limited to non-commercial research.
Meituan upgraded its open-source digital human model LongCat-Video-Avatar to 1.6. It uses the MIT license, so commercial use is allowed. Lip movement looks more natural, and long videos no longer drift from the original face as they grow. It also runs faster. Learn what it can do, how to run it on a regular graphics card, and get a prompt that lets your AI agent judge whether your computer can run it and which route to take.
