transducer about speech HOT 5 OPEN

Yes great point. In the committed code the ground truth labels are being used for the transducer. I have some code to do this properly using the inferred output but I haven't had a chance to clean it up and commit it yet. That's why I haven't posted "transducer" results in the README yet.

from speech.

And yes, I will continue to support this project though any collaborators would be very welcome!!

from speech.

@awni Have you made any progress on cleaning up the decoder?

from speech.

Just for reference, here is my inference code.
https://gist.github.com/yjchun/aae0b86f89ffb46a54c28e7747124ee4

May not be useful as it is because it uses my model class's internal logic.
The problem is inference is awfully slow. Takes 3 seconds for 10 seconds of audio with 400 hidden layers. 161 chars = 161 prediction+joint network calls at minimum.
Had to read Grave's paper in and out for a few days for this piece of code.

And thank you @awni for sharing your transducer loss implementation which was very helpful.

from speech.

Here is my implement for greed decoder.
you may need some change for your lstm decoder network.

from speech.