Clarification of DAC decoder provenance and licence for UK commercial use

未关闭
#76 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
12/100
Issue 类型
文档
描述清晰度
需要澄清
活跃度
活跃
技术栈
python

调研方向

This is a licensing question for the maintainers, not a code change. Start by reading the attribution and header comments in mova/diffusion/models/dac_vae.py, then check the repository's LICENSE and any NOTICE files for the Apache-2.0 declaration. Done means maintainers post the exact upstream revisions, the licence for each adapted portion, and the provenance of the audio_vae weights.

由索引模型根据 Issue 内容生成。

描述

We are reviewing MOVA revision 1591b2557b42030a3421442c998dd6f5602ed9bd and MOVA-360p revision eab4aa91d6d5eb515e259a0c8533c90062b117a5 for a UK-hosted commercial service.

The inference decoder in mova/diffusion/models/dac_vae.py identifies HunyuanVideo-Foley as its adaptation source. That project's top-level licence excludes the UK, while MOVA declares Apache-2.0.

Could you identify the exact original revisions and separate licences covering the adapted decoder, any additional permission to redistribute those portions under Apache-2.0, and the provenance/licence of the audio_vae weights? Please distinguish original MIT Descript code from later modifications. If applicable, is there a fully permissive replacement supported by the same weights?

We have not approved this component for commercial release while the provenance remains unresolved.

主要语言
Python
星标
1.1k
派生
97
PR 合并指标
30 天内没有已合并 PR

环境准备

这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

OpenMOSS/MOVA 的其他 Issue

查看 OpenMOSS/MOVA 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。