issues Search Results · repo:cwx-worst-one/EAT language:Python
Filter by
13 results
(56 ms)13 results
incwx-worst-one/EAT (press backspace or delete to remove)Hi the installation with Fairseq has been a bit of a headache ,I have tried multiple versions of python to check and run
it , also since that isn t functioning has anyone tired fairseq2 to run this and ...
Abhishekdileep
- Opened 6 days ago
- #14
Thank you for your excellent work and for open-sourcing all these codes.
I ve recently found that when restarting the pre-training task from a halfway checkpoint (e.g. checkpoint_last.pt), the
EMA decay ...
pending
jianganbai
- 2
- Opened 9 days ago
- #13
i have a dataset , but the audio is all 2 seconds . i dont want pretraining from scratch,
Masquerades2015
- 2
- Opened 24 days ago
- #12
Hi there,
Thank you for sharing your excellent work!
I am having trouble understanding how the loss is calculated during pretraining. Could you help clarifying some details,
please?
So far, I have noticed ...
roskoN
- 2
- Opened on Oct 17, 2024
- #11
Hey there!
Congratulations on the model and thanks for open sourcing!
I would like to finetune EAT on my own dataset for audio classification. Is it possible?
If so, would the best pipeline be to just ...
cvillela
- 4
- Opened on Aug 21, 2024
- #9
Hi, while I m trying to run the script, I cannot find which script should I modify to change the number of epochs. How
can I set the number of epochs?
WGook
- 1
- Opened on Aug 21, 2024
- #8
Hi, is there any tutorial on how to pre-train EAT on own data? I d like to pre-train it on a LightningDataModule, but I
have no clue if it s compatible with all this fairseq stuff. I would be very grateful ...
aalbayrak394
- 1
- Opened on Aug 2, 2024
- #7
您好,我想请教一下feature_extract.py对应的是否是EAT作为Audio Encoder的输出?
我运行feature_extract.py之后输出是一个[512,1024]的tensor。实际上我想用EAT做编码器用于AAC任务,我直接复用feature_extract方法可以吗?
我了解到贵团队的“SLAM-LLM”已经在此基础上集成了该功能,其中示例examples/aac_audiocaps/scripts/inference_eat_audiocaps.sh的line31: ...
zhangron013
- 2
- Opened on Jul 25, 2024
- #6
您好!我在使用 bash EAT/scripts/feature_extract.sh 提取音频时遇到错误“TypeError: forward() got an unexpected keyword argument
padding_mask ”。下面是详细报错,是不是我装的某些依赖的版本不对?我应该怎么fix呢?
Traceback (most recent call last):
File ...
zhangron013
- 5
- Opened on Jul 24, 2024
- #5

Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.