MiniMax-AI / MiniMax-AI/MiniMax-Music3
永远无法唱完歌词，怎么控制每个标签内的时长呢
Open
Nobody has claimed this yet.
- Dominant language
- No language data
- Stars
- 896
- Forks
- 84
- PR merge metrics
- No merged PRs in 30d
Description
[Intro]我都删了，可每次生成都要生成固定比例的开场曲，20秒的开场有啥用。 无论怎么调整时长永远都无法唱完歌词。 这个text encoder 不会规划时间，时间到了音乐马上戛然而止。而不是根据设置的时长内确保唱完
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by examining the lyric-tag handling, fixed Intro generation, duration controls, and text encoder behavior described in the report. Reproduce a generation with the [Intro] section removed and lyrics longer than the configured duration. Done means tag-specific duration behavior is defined and the generated music completes the lyrics without ending abruptly.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, audio-video-rtc
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100