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

加载模型时显示加载失败 #74

Closed
dzk457470350 opened this issue Jan 15, 2024 · 11 comments
Closed

加载模型时显示加载失败 #74

dzk457470350 opened this issue Jan 15, 2024 · 11 comments

Comments

@dzk457470350
Copy link

本人纯小白,下载安装好本体后再下载模型到C盘,在加载后显示模型加载失败,求告知原因与解决方法~
2024115233314

@CheshireCC
Copy link
Owner

模型配置文件缺失了

@dzk457470350
Copy link
Author

谢谢回答,我刚刚从已关闭的回答里找到了,正在重新尝试下载

@dzk457470350 dzk457470350 reopened this Jan 15, 2024
@dzk457470350
Copy link
Author

在尝试了关闭的问题中的解决方法后,依然没能解决问题
QQ图片20240116000557

@CheshireCC
Copy link
Owner

加载失败的时候去看看 日志文件

@dzk457470350
Copy link
Author

-model_size_or_path: D:/backup/whisper-large-v2-ct2-32
-device: cuda
-device_index: 0
-compute_type: float32
-cpu_threads: 4
-num_workers: 1
-download_root: D:\FasterWhisperGUI\cache2
-local_files_only: False
-use_v3_model: False
Traceback (most recent call last):
File "D:\FASTER1\faster_whisper_GUI\modelLoad.py", line 41, in run
File "D:\FASTER
1\faster_whisper_GUI\modelLoad.py", line 73, in loadModel
File "D:\FASTER~1\faster_whisper\transcribe.py", line 128, in init
RuntimeError: CUDA failed with error out of memory

@CheshireCC
Copy link
Owner

显存不够,你需要确保有至少 6GB 以上空闲显存才能加载 32 位模型,我发现你使用的是 int8 的模型,那么将量化方式改为 int8 吧

@dzk457470350
Copy link
Author

对的 我显卡只有6GB显存 但是我不会将量化方式改为 int8 请问该如何操作

@CheshireCC
Copy link
Owner

计算精度那里选一下
image

@dzk457470350
Copy link
Author

模型加载成功!非常感谢!
QQ图片20240116015541

@CheshireCC CheshireCC pinned this issue Jan 15, 2024
@tomeleon
Copy link

tomeleon commented May 8, 2024

我这里也是加载模型失败,日志显示是:
Traceback (most recent call last):
File "C:\PROGRA2\FasterWhisperGUI\faster_whisper_GUI\modelLoad.py", line 41, in run
File "C:\PROGRA
2\FasterWhisperGUI\faster_whisper_GUI\modelLoad.py", line 73, in loadModel
File "C:\PROGRA~2\FasterWhisperGUI\faster_whisper\transcribe.py", line 143, in init
Exception: Model "openai/whisper-tiny" on the Hub doesn't have a tokenizer

@CheshireCC
Copy link
Owner

检查模型文件夹下的文件是否完整

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

3 participants