Subscribe

What are you looking for?

Main Menu

明報新聞網

小米發布開源聲音理解大模型MiDashengLM-7B

Future Wealths
Future Wealths
4 8 月, 2025
One Min Read
6 Views
0 Comments
小米(1810)在微信公布，發布和全量開源的MiDashengLM-7B模型，基於Xiaomi Dasheng作為音頻編碼器和Qwen2.5-Omni-7B Thinker作為自回歸解碼器，通過創新的通用音頻描述訓練策略，實現了對語音、環境聲音和音樂的統一理解。

原文: https://finance.mingpao.com/fin/instantf/20250804/1754277688627/%E5%B0%8F%E7%B1%B3%E7%99%BC%E5%B8%83%E9%96%8B%E6%BA%90%E8%81%B2%E9%9F%B3%E7%90%86%E8%A7%A3%E5%A4%A7%E6%A8%A1%E5%9E%8Bmidashenglm-7b%22%20target=%22blank

Last Update: 4 8 月, 2025

Please share this article if you like it!

Link Copied!
Future Wealths
Written By

Future Wealths

Other Articles

Related Posts

Our site uses cookies. By using this site, you agree to the Privacy Policy and Terms of Use.

Accept