Currently, some models in this project lack multimodal integration tests for audio input types. Mistral AI in pr has added audio input but lacks relevant integration tests . I will make my contribution in this regard and submit my PR as soon as possible. Also, thanks to @YunKuiLu for the help 🙏😊(my English is not very good.) This is the Chinese translation. If there are any unclear expressions, please let me know and I will supplement them in time.
Comment From: CodeCodeAscension
目前,该项目缺乏针对音频输入类型的多模态集成测试(来自 #3903(评论))。我将在这方面做出贡献,并尽快提交我的 PR。另外,感谢您的帮助🙏😊(我的英语不好。这是中文翻译。如有不清楚的表达,请告知,我会及时补充)
I'm dealing with this problem
Comment From: ilayaperumalg
@CodeCodeAscension Thank you for your interest! Looking forward to your contributions