-
Notifications
You must be signed in to change notification settings - Fork 10
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
about the training details and asking for model checkpoint #2
Comments
Hey @ChangLee0903 ! Thanks for the feedback! I am not sure what you mean by training cost. Personally, I did not use state-of-the-art GPUs (NVIDIA GeForce GTX 1080 Ti ones), so most experiments took me about 12-15 hours on a single GPU depending on the experiment. Yes, I started with a clean speech checkpoint to train the robust ASR (to save compute effort and to start with a reasonable ASR system). This link will point you to the training command used for the base clean speech model along with the download link for the checkpoint. Hope this clarifies your questions. |
Thx 10 billions for your fast reply, all of my questions have been answered. I'll cite you if my paper publish. |
Hi @archiki, best, |
The difference between the WER and CER numbers must be due to the difference in beam-decoding parameters like |
Hi @archiki, Thx for ur reply, the arguments I concern is about "--learning-anneal 1.01 --batch-size 64 -- best, |
Yes, @ChangLee0903, these arguments are taken from the checkpoint. Note: |
Hi @archiki,
I appreciate this work very much, and thanks for providing the implementation. Could you please tell me that how long does the training cost? BTW, did you take the model checkpoint trained from clean corpus as the initial parameters to train the robust ASR? May I ask your checkpoints?
best,
Chi-Chang Lee
The text was updated successfully, but these errors were encountered: