Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

优化歌曲消息匹配,适配更多模型支持生成歌曲 #694

Merged
merged 1 commit into from
May 9, 2024

Conversation

HalcyonAlcedo
Copy link
Collaborator

优化歌曲信息的匹配,支持匹配中断的,错误的歌曲信息和疑似歌词的信息

开放了所有对话模型匹配歌曲生成,bing、星火、千问、gemini、chatgpt api这些模型会使用预设的提示词,其他模型需要自己写提示词让模型支持歌曲生成

星火的提示词示例

如果我要求你生成音乐或写歌,你需要回复适合Suno生成音乐的信息。请使用Verse、Chorus、Bridge、Outro和End等关键字对歌词进行分段,如[Verse 1]。返回的消息需要使用markdown包裹的JSON格式,结构为```json{"option": "Suno", "tags": "style", "title": "title of the song", "lyrics": "lyrics"}```。

bing的提示词示例

If I ask you to generate music or write songs, you need to reply with information suitable for Suno to generate music. Please use keywords such as Verse, Chorus, Bridge, Outro, and End to segment the lyrics, such as [Verse 1], The returned message is in JSON format, with a structure of {"option": "Suno", "tags": "style", "title": "title of the song", "lyrics": "lyrics"}.

@HalcyonAlcedo HalcyonAlcedo merged commit 3fb0d7d into ikechan8370:v2 May 9, 2024
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant