You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the feature
Please describe the feature requested here(请在这里描述需求)
使用qwen2.5-omni推理时,目前智能保存文本输出,无法保存音频输出,这对于一个多模态输出的模型来说,效果大打折扣,看到huggingface都已经实现这个过程,希望swift能接入一下。 Paste any useful information
Paste any useful information, including papers, github links, etc.(请在这里描述其他有用的信息,比如相关的论文地址,github链接等) https://huggingface.co/Qwen/Qwen2.5-Omni-7B Additional context
Add any other context or information here(其他信息可以写在这里)
The text was updated successfully, but these errors were encountered:
---原始邮件---
发件人: ***@***.***>
发送时间: 2025年4月16日(周三) 晚上6:18
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [modelscope/ms-swift] 希望增加qwen2.5-omni推理保存音频文件 (Issue #3898)
哥你好,请教一下你通过swift部署qwen2.5-omni模型用的是NPU还是GPU
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
hjjjk left a comment (modelscope/ms-swift#3898)
哥你好,请教一下你通过swift部署qwen2.5-omni模型用的是NPU还是GPU
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
Describe the feature
Please describe the feature requested here(请在这里描述需求)
使用qwen2.5-omni推理时,目前智能保存文本输出,无法保存音频输出,这对于一个多模态输出的模型来说,效果大打折扣,看到huggingface都已经实现这个过程,希望swift能接入一下。
Paste any useful information
Paste any useful information, including papers, github links, etc.(请在这里描述其他有用的信息,比如相关的论文地址,github链接等)
https://huggingface.co/Qwen/Qwen2.5-Omni-7B
Additional context
Add any other context or information here(其他信息可以写在这里)
The text was updated successfully, but these errors were encountered: