-
Notifications
You must be signed in to change notification settings - Fork 31
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
your greed decode implement is wrong. #1
Comments
Its based on the assumption that for each acoustic feature frame, there is at most one corresponding label, so we just need to move one step up, then turn right. I implemented the greedy decode several weeks ago as your way, but the PER is worse in TIMIT. The decoding algorithm is still under developing, so any comments are welcome. |
but in my dataset my greedy decode implement CER is 15% lower than yours. |
Which dataset did you use? I'll check that again in TIMIT. |
In the paper of alex grave, in a transducer path ,only the label is null, the frame will step. when the label is not null ,the U will increase,But the T will stop to wait. |
in my private dataset,only when use the second method ,the rnn transducer will compare with ctc. |
@Duum I'll check your implementation and reply to you asap. |
@Duum By the way, what you mean "the second method" ? Have you ever try beam search ? |
the second method is my implement of greedy decode,I haven't use beam search for now . |
@Duum Thanks for your comments, I'll check that. |
I think your transducer greed decode implement is wrong.
here is my implement of pytorch.
The text was updated successfully, but these errors were encountered: