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

repetition 问题记录 #128

Open
fclearner opened this issue Aug 6, 2024 · 0 comments
Open

repetition 问题记录 #128

fclearner opened this issue Aug 6, 2024 · 0 comments

Comments

@fclearner
Copy link

fclearner commented Aug 6, 2024

大模型重复生成问题

推理层面优化:
repetition penalty

训练层面优化:
eos_token: QwenLM/Qwen2.5#779 (comment)
no_speech token: #113
模型帧率,提高帧率可以改善短音频复读机问题
LLM的文本分布
引入ctc结果:https://arxiv.org/abs/2408.09491

从NLP的角度:
https://zhuanlan.zhihu.com/p/672261242?utm_psn=1807773013061558274

训练数据中短文本或重复文本较多,即数据多样性不足时会触发大模型重复生成问题
模型参数量越小越容易触发大模型重复生成问题

欢迎补充!

@fclearner fclearner mentioned this issue Nov 14, 2024
2 tasks
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