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

训练与推理对音频的预处理不一样是什么原因?这个会对模型推理的效果有影响吗 #185

Closed
zhangyuzyy opened this issue Aug 28, 2024 · 2 comments

Comments

@zhangyuzyy
Copy link

请问一下,训练与推理对音频的预处理不一样是为什么?
训练:
使用/scripts/data.py中的代码
whisper_feature = audio_processor.audio2feat(audio_path)
将whisper_feature 保存成了npy,然后使用DataLoader

推理时使用的scripts/finetuned_inference.py中的代码
whisper_feature = audio_processor.audio2feat(audio_path)
whisper_chunks = audio_processor.feature2chunks(feature_array=whisper_feature,fps=fps)

为什么在训练的时候,不需要使用 audio_processor.feature2chunks方法呢?

@czk32611
Copy link
Contributor

hello,在https://github.com/TMElyralab/MuseTalk/blob/train_codes/train_codes/DataLoader.py#L195进行feature2chunks了。这样保存的空间会小一些

@zhangyuzyy
Copy link
Author

感谢,理解了

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

2 participants