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

输入的歌词并没有唱完 #85

Open
gmm111 opened this issue Feb 28, 2025 · 0 comments
Open

输入的歌词并没有唱完 #85

gmm111 opened this issue Feb 28, 2025 · 0 comments

Comments

@gmm111
Copy link

gmm111 commented Feb 28, 2025

输入参数:python infer.py
--cuda_idx 0
--stage1_model m-a-p/YuE-s1-7B-anneal-zh-cot
--stage2_model m-a-p/YuE-s2-1B-general
--genre_txt ../prompt_egs/genre_zh_rap-1.txt
--lyrics_txt ../prompt_egs/lyrics_zh_rap-1.txt
--run_n_segments 6
--stage2_batch_size 6
--output_dir ../output
--max_new_tokens 6000
--repetition_penalty 1.2
歌词:

[verse]
在浦江之畔曙光初放
万众科技的旗帜飞扬
怀揣着梦想勇敢起航
智慧的光芒照亮前方

[verse]
数据的海洋我们闯荡
精准分析是致胜秘方
每一次探索充满希望
为行业发展贡献力量

[verse]
团队的协作坚不可挡
心与心相连凝聚能量
用专业态度书写篇章
挑战中我们越战越强

[verse]
诚信的理念刻在心上
服务客户是不变信仰
每一个细节精心考量
赢得那信任目光闪亮

[verse]
上海万众科技闪耀光芒
引领着行业迈向新的方向
用热血拼搏铸就辉煌
未来的路上豪情万丈

问题描述:生成的音乐歌词的最后一段verse没唱,歌曲就结束了。增加参数的max_new_tokens 和run_n_segments 还有stage2_batch_size 数据生成的音乐还是会出现同样的问题,最后一段没有唱。请问是什么问题,如何解决?

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

No branches or pull requests

1 participant