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
configuration files for the "no pre-training" setups #15
Comments
Hi, To train a model from scratch, you can simply use the config files in The best hyperparameters for training from scratch might also differ from those with pre-training, so you may need to tune hyperparameters a bit such as number of updates, warmup steps, etc. |
Thank you for details! I have made the config file and it seems to be uploaded successfully, but here comes an issue:
I have googled and find the problem lies in the import order of |
Hi, I have sovled this issue, I find another issue that deserves your notice, the class |
Hi, Thank you for reporting this issue. The |
yep, thanks a lot! |
Hi authors, I wonder if all the systems in Table 3 are finetuned on clean data (instead of noisy data)? |
Hi, The models in table 3 are fine-tuned on noisy data. |
Thank you for quick reply. But I feel some confusing, if models in table 3 are fine-tuned on noisy data, then compare table 3(a) and table 4(d) above, under the same train setting (no pretrain + 30h noisy data finetune), the LARGE model performs even worse than BASE model by 15%, which is abnormal:( |
Hi, This is probably due to overfitting of the large model in this low-resource setting. |
Oh I see, thanks a lot. |
Hi authors,
Thank you for sharing such nice research work! Thanks to your previous help, I have successfully completed the LRS3 and MUSAN data preparation.
I am now intersted in directly finetune the AVSR system (without pretraining, because of computing resource limits), and hope to reproduce the following highlighted systems in the paper "Robust Self-Supervised Audio-Visual Speech Recognition":
I wonder if you can share the config files for these four systems?
If inconvenient, can you guide me some details on how to modify the existed config files in directory
conf/av-finetune/
? I am new in this field and don't know how to do this, hope you can help me:)Thank you very much!!
The text was updated successfully, but these errors were encountered: