Anyone able to get tf serving to work with the custom ctc beam op using the lm model

[JRMeyer]

>>> domenicrosati
[January 26, 2018, 10:13pm]

Hello,

I am using a model trained with DeepSpeech in tf serving just fine.
However without using the custom decoder my WER is around 16%. I
exported the model using the custom decoder but when I loaded it into tf
serving I received

Loading servable: {name: speech_detection version: 1} failed: Not found: Op type not registered 'CTCBeamSearchDecoderWithLM' in binary running on c41d408c3a94. Make sure the Op and Kernel are registered in the binary running in this process.

has anyone resolved thus issue?

I figured I could attempt a rebuild of tf serving with the .so files
included in the BUILD file but wanted advice before I started
investigating.

Thanks, slash
Dom

P.s. slash
I understand tf serving is not supported. I am just wondering if anyone
encountered this. I am happy to make a PR to the docs for how to get the
model in serving working without (and hopefully with)the decoder

[This is an archived TTS discussion thread from discourse.mozilla.org/t/anyone-able-to-get-tf-serving-to-work-with-the-custom-ctc-beam-op-using-the-lm-model]

[JRMeyer]

>>> lissyx
[January 27, 2018, 9:33pm]

Loading the module requires specific handling code in DeepSpeech.py,
likely you have to do something similar for serving?

[
[[erniemargatapinnock
[January 27, 2018, 10:47pm]

[Archived Post]

[JRMeyer]

>>> domenicrosati
[February 2, 2018, 11:23am]

I think I will probably do as you say and implement the decoder after i
recieve the response from the call to tf-serving. That way I won't have
to manage tf-serving builds ECT, I can just use the decoding logic with
that custom op in tf session in my app code.

I will let you know how it goes

[Archived Post]