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

Beamsearch for decoding instead of the current greedy search. #54

Closed
bmilde opened this Issue Nov 3, 2016 · 1 comment

Comments

3 participants
@bmilde

bmilde commented Nov 3, 2016

Decoding is currently done with a greedy max for each decoding step. This will (severely) limit the performance of the model when you use it, as only the probability of the next phoneme character is maximized and not the probability of the whole phoneme sequence. Using beam search, a better log probability for the whole phoneme sequence could be found. I suggest to implement beam search by changing Tensorflows seq2seq decoding so that the decoding can be done step wise and then the beam search can be handled in Python.

This Tensorflow issue is related tensorflow/tensorflow#654, some comments shared code of extended implementations with beam search.

@nurtas-m

This comment has been minimized.

Collaborator

nurtas-m commented May 8, 2018

Solved in new versions of g2p-seq2seq starting from 6.0.0a0.

@nurtas-m nurtas-m closed this May 8, 2018

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment