-
I think your transducer greed decode implement is wrong.
here is[ my implement of pytorch](https://github.com/sequence-labeling/transducer_greed_decoder).
-
Hello!
I've recently updated to tensorflow version 1.5.0, and suddenly receive an error, that I can't decipher, for code that worked before (in version 1.4.1): `Cannot use 'transducer_training/whil…
-
Hello!
I believe to have found a bug in Tensorflow when running the code below. I am currently trying to build a neural transducer, and have stumbled across TF sometimes not returning any values for …
-
Hello!
I believe to have found a bug in Tensorflow when running the code below. I am currently trying to build a neural transducer, and have stumbled across TF sometimes not returning any values for …
-
Hello!
I believe to have found a small bug when using the `zero_state(batch_size, tf.float32).clone(cell_state=encoder_state)` command. When batch size is 1, the error `ValueError: The shape for deco…
-
Hi,
I'd like to explore using scrappie as a library as a replacement for nanopolish's HMM. I've got a hacked up version of the original scrappie code working in a branch but I needed to make a few …
-
Context-Dependent Confusion Rules for OCR Post-Processing
-
I'm trying to integrate this system with another one built with Tensorflow.
I don't have the audio data. I would be grateful if someone can provide a sample file decoded with net-output-extract (as i…
-
Thank you for this awesome package. Much wow.
I cannot use _dp_ which all examples are based on (https://github.com/Element-Research/rnn/issues/60).
So I have to make sure _optim_ is supported for ar…
ghost updated
8 years ago
-
Hey guys,
I am currently writing and testing some minimalexamples of this repo.
I have one problem with understanding the way I should handle sequencer in models, e.g. nested sequencer.
Can anybody…