Skip to content

1.5B-Long 模型倾向于生成人声？ #61

New issue
New issue
Open
Open
1.5B-Long 模型倾向于生成人声？#61
@opencvbaby

Description

@opencvbaby
opencvbaby
opened on Dec 7, 2025

测试中发现挺多音频中都包含含糊不清的人声，如何约束更好的生成纯音乐？

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions